© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37778
    Prev
    Next
    INDEX
    Explanations

    weight loss or gain

    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
    اص
    -0.09
    累计
    -0.09
    weg
    -0.09
    çĮĹ
    -0.09
    пÑĭ
    -0.09
     Mort
    -0.08
    orest
    -0.08
     racks
    -0.08
    深度
    -0.08
    æł·åŃIJ
    -0.08
    POSITIVE LOGITS
    åģķ
    0.09
    gain
    0.09
     gain
    0.09
    -related
    0.09
    åĭī
    0.08
    åŃ©ç«¥
    0.08
    åıijå±ķçIJĨ念
    0.08
    agan
    0.08
    borne
    0.08
    éĶģå®ļ
    0.08
    Activations Density 0.013%

    No Known Activations