© 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. 23117
    Prev
    Next
    INDEX
    Explanations

    legislative bodies and members

    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
    ç¬ijèĦ¸
    -0.08
     SM
    -0.08
    å·²ä¹ħ
    -0.08
    åŁºå±Ĥ
    -0.08
    ä¿©
    -0.08
    å¼ķèµ·
    -0.08
    OMB
    -0.08
    cab
    -0.08
    iga
    -0.08
    åħ¬åı¸åľ¨
    -0.08
    POSITIVE LOGITS
     Kurd
    0.09
    ereum
    0.09
    ç½®æį¢
    0.09
    ä¹Ļ
    0.09
    éĩĮçļĦ
    0.09
    athed
    0.09
     Ñģамо
    0.09
    æİĴéĻ¤
    0.08
     deputies
    0.08
    çİĭåŃIJ
    0.08
    Activations Density 0.069%

    No Known Activations