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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110765
    Prev
    Next
    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    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
    __))
    -0.07
     leader
    -0.07
    Control
    -0.07
    soap
    -0.07
    fat
    -0.07
    _BY
    -0.06
    VOKE
    -0.06
     squid
    -0.06
    crate
    -0.06
    מטוס
    -0.06
    POSITIVE LOGITS
    انب
    0.07
    (expr
    0.07
     שנית
    0.07
     motivated
    0.07
     różnic
    0.07
     الدني
    0.06
    Inject
    0.06
    Unchecked
    0.06
     Anim
    0.06
    -aligned
    0.06
    Activations Density 0.027%

    No Known Activations