© 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. 17700
    Prev
    Next
    INDEX
    Explanations

    Parliament or political bodies

    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
    lsa
    -0.09
    ancode
    -0.09
    éĺ¶çº§
    -0.09
    åĪĨéĶĢ
    -0.09
    _sector
    -0.09
     ún
    -0.09
    xbe
    -0.08
     вÑĭÑħод
    -0.08
    SOLE
    -0.08
    _AA
    -0.08
    POSITIVE LOGITS
    åĬ¿
    0.09
     NOP
    0.09
    æī¶
    0.09
    çijŁ
    0.09
    åı¯è§Ĥ
    0.09
    楼ä¸Ĭ
    0.09
    ä¼ī
    0.09
    çķĻåľ¨
    0.08
    åħ¬åŃIJ
    0.08
    åĮºåŁŁæĢ§
    0.08
    Activations Density 0.068%

    No Known Activations