© 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. 31781
    Prev
    Next
    INDEX
    Explanations

    service quality

    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
     stripper
    -0.10
    人æ°Ķ
    -0.10
    èħŃ
    -0.09
    身åŃIJ
    -0.09
    мел
    -0.09
    æīĵå¼ĢäºĨ
    -0.08
    ilate
    -0.08
    igel
    -0.08
    _asc
    -0.08
    èĢģæŧå°ıåĮº
    -0.08
    POSITIVE LOGITS
    æľįåĬ¡æ°´å¹³
    0.11
    åħ¬åijĬ
    0.10
    SPEC
    0.10
    çķĮå®ļ
    0.09
    ä¿Ŀè¯ģ
    0.09
    çľ©
    0.09
    ä¿Ŀéļľ
    0.09
    æī¿è¯º
    0.09
    æľįåĬ¡è´¨éĩı
    0.09
    æĢ§èĥ½
    0.09
    Activations Density 0.099%

    No Known Activations