© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52483
    Prev
    Next
    INDEX
    Explanations

    actor as character

    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
    èħ°éĥ¨
    -0.09
    å¾Ĺ天
    -0.09
    à¹Ĥà¸Ĺษ
    -0.09
    itime
    -0.09
    åĩłå¼ł
    -0.09
    itz
    -0.08
    身为
    -0.08
    %i
    -0.08
    cec
    -0.08
    çĬ¯
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.10
    çļĦèĥĮåIJİ
    0.10
    èģĶ
    0.09
    èĽŁ
    0.09
    çļĦç¼ĺæķħ
    0.08
    .nih
    0.08
    çļĦè¯Ńè¨Ģ
    0.08
    åĢľ
    0.08
    _RET
    0.08
    å½ĵçĦ¶
    0.08
    Activations Density 0.036%

    No Known Activations