Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 7335
    Prev
    Next
    INDEX
    Explanations

    sad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    消費
    -0.08
    [block
    -0.07
    overlap
    -0.07
    씻
    -0.07
     wym
    -0.06
     Screening
    -0.06
    棨
    -0.06
    (lib
    -0.06
    _ALLOC
    -0.06
    	del
    -0.06
    POSITIVE LOGITS
     �
    0.08
     Lesser
    0.07
    udents
    0.07
    낮
    0.07
    2
    0.07
     Ballard
    0.07
    .apply
    0.06
    down
    0.06
    电站
    0.06
    っていない
    0.06
    Activations Density 0.008%

    No Known Activations