© 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
    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. 41705
    Prev
    Next
    INDEX
    Explanations

    semicolon

    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
    魔术
    -0.08
     xmlns
    -0.07
     darken
    -0.07
    :"+
    -0.07
    successfully
    -0.07
     Enh
    -0.06
    _String
    -0.06
    cite
    -0.06
    基辅
    -0.06
    "c
    -0.06
    POSITIVE LOGITS
    -negative
    0.07
    -tier
    0.07
    _FACE
    0.06
    .record
    0.06
    -zA
    0.06
    GER
    0.06
    ubar
    0.06
    .capacity
    0.06
    .Constraint
    0.06
    Same
    0.06
    Activations Density 0.018%

    No Known Activations