© 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. 55588
    Prev
    Next
    INDEX
    Explanations

    depth, penetration, into

    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
    以人为
    -0.10
    ä»·
    -0.09
    çģ«èĬ±
    -0.09
     ÑĥÑģи
    -0.09
    åı¯æĥ³
    -0.09
    pair
    -0.09
    endir
    -0.09
    å¿łè¯ļ
    -0.08
     Spread
    -0.08
     spread
    -0.08
    POSITIVE LOGITS
    深度
    0.13
    _DEPTH
    0.10
    è´¯
    0.10
    ä¸īåĪĨä¹ĭä¸Ģ
    0.09
    åħ¥åºĵ
    0.09
    æĮ¤
    0.09
    _depth
    0.09
    â¼Ĭ
    0.09
    -auto
    0.09
    Depth
    0.09
    Activations Density 0.045%

    No Known Activations