© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20663
    Prev
    Next
    INDEX
    Explanations

    up to

    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
    Ñĥв
    -0.11
    ãģIJ
    -0.11
    ONGL
    -0.09
    uzu
    -0.09
     Garr
    -0.09
    สล
    -0.09
    osc
    -0.09
    æłĿ
    -0.09
    ä¸ĢåĪĩéĥ½
    -0.08
    everything
    -0.08
    POSITIVE LOGITS
    çļĦåľ°æŃ¥
    0.09
    åģľè½¦
    0.08
    ä¹İ
    0.08
    åĥ»
    0.08
    为æŃ¢
    0.08
    åīįè¿°
    0.08
    ä¸īå±Ĥ
    0.08
    well
    0.08
    éĥ½æĹłæ³ķ
    0.08
    ä¸»å¼ł
    0.08
    Activations Density 0.063%

    No Known Activations