© 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. 59018
    Prev
    Next
    INDEX
    Explanations

    Yates, Cato, Palmyra, Capoeira

    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
    è¿ŀéĶģ
    -0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    _VOID
    -0.08
     Laura
    -0.08
    åĬ©æīĭ
    -0.08
    éĢłä»·
    -0.08
    hunt
    -0.08
    sett
    -0.08
    ä¸ļä½Ļ
    -0.08
    åĦ¿ç«¥
    -0.08
    POSITIVE LOGITS
    æ¡ħ
    0.10
    ieri
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
    è··
    0.09
    æľºèº«
    0.09
    åĿŀ
    0.08
    StdString
    0.08
    ç¿ĺ
    0.08
    à¸Ńà¸ĩ
    0.08
    èĭĩ
    0.08
    Activations Density 0.001%

    No Known Activations