© 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. 6615
    Prev
    Next
    INDEX
    Explanations

    negative effects or behavior

    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
    ä¸įéĶĻçļĦ
    -0.10
    èĥľè´Ł
    -0.09
    SAFE
    -0.09
    stp
    -0.09
    odal
    -0.09
    _DECLARE
    -0.09
     McGregor
    -0.09
     há»ĵng
    -0.09
    acement
    -0.09
    หลวà¸ĩ
    -0.09
    POSITIVE LOGITS
     luck
    0.10
    uge
    0.10
     Beg
    0.09
    ish
    0.09
    ä¸Ŀä¸Ŀ
    0.09
    ities
    0.09
    æİīäºĨ
    0.08
    itated
    0.08
    ging
    0.08
    ur
    0.08
    Activations Density 0.039%

    No Known Activations