© 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. 54688
    Prev
    Next
    INDEX
    Explanations

    debts, taxes, and funding

    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
    éĢļ车
    -0.09
    éĩijéĴ±
    -0.09
    arent
    -0.09
    çŁ¥æĻĵ
    -0.09
    太éĺ³èĥ½
    -0.09
    丰
    -0.08
    æľķ
    -0.08
    ä¸ļä½Ļ
    -0.08
    éĢĤæŶ
    -0.08
     Hanson
    -0.08
    POSITIVE LOGITS
    /respond
    0.10
    宫殿
    0.10
    çĨµ
    0.09
    åĽŀåºĶ
    0.09
    çŃĽ
    0.09
    åĹ·
    0.08
    çIJ¨
    0.08
    åĽŀåĪ°
    0.08
    _imm
    0.08
    çħ§æł·
    0.08
    Activations Density 0.037%

    No Known Activations