© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 112747
    Prev
    Next
    INDEX
    Explanations

    batter

    np_max-act · gemini-2.0-flash

    the neuron detects the token sequence/word stem "batter" (including morphological extensions like "battering").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SQ
    -0.08
    IZ
    -0.08
    Pop
    -0.07
    伊
    -0.07
    AMB
    -0.07
    Kim
    -0.07
    eness
    -0.07
     Kub
    -0.07
    _FM
    -0.07
    Ace
    -0.07
    POSITIVE LOGITS
    ⌨
    0.07
     plat
    0.07
    etten
    0.07
    황
    0.07
    attered
    0.07
    大家都
    0.07
    graphic
    0.06
    	mysqli
    0.06
    都能够
    0.06
    صور
    0.06
    Activations Density 0.007%

    No Known Activations