© 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. 15-RESID-POST-AA
    11. 82071
    Prev
    Next
    INDEX
    Explanations

    UI

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蕃
    -0.08
    点
    -0.08
    =k
    -0.08
    odal
    -0.07
    这片
    -0.07
    ’
    -0.07
     Denis
    -0.07
    -base
    -0.07
     Mediterranean
    -0.07
    _pts
    -0.07
    POSITIVE LOGITS
    隍
    0.08
    :["
    0.07
    靛
    0.07
     języ
    0.07
    ื
    0.07
    	LOGGER
    0.07
    工業
    0.07
    0.07
     הית
    0.06
     FOLLOW
    0.06
    Activations Density 0.018%

    No Known Activations