© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27473
    Prev
    Next
    INDEX
    Explanations

    violation or violates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ൾ
    -0.11
    ablish
    -0.10
    алÑĮн
    -0.10
    resse
    -0.09
     оÑĤкÑĢÑĭва
    -0.09
     dÃłng
    -0.09
    ellation
    -0.09
    .ColumnHeader
    -0.08
    combe
    -0.08
    eral
    -0.08
    POSITIVE LOGITS
    ties
    0.09
    rance
    0.09
    eng
    0.09
     lẽ
    0.09
    Occurred
    0.09
    èĢħçļĦ
    0.09
    raries
    0.09
    áp
    0.09
    ubic
    0.08
    ance
    0.08
    Activations Density 0.012%

    No Known Activations