© 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. 54518
    Prev
    Next
    INDEX
    Explanations

    giving or providing something

    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
    èĢĮæĿ¥
    -0.09
    è°ĥæŁ¥æĺ¾ç¤º
    -0.09
    TypeInfo
    -0.09
    æĺ¯éĿŀ
    -0.08
    mania
    -0.08
    åĽĽåij¨
    -0.08
    bab
    -0.08
    é»Ŀ
    -0.08
    ifes
    -0.08
    gard
    -0.08
    POSITIVE LOGITS
    åįļçī©
    0.10
    æ¿ł
    0.09
    æĨ¬
    0.09
    endants
    0.09
    .ret
    0.09
    еÑĩение
    0.09
    é¹°
    0.09
    豸
    0.09
    -ret
    0.09
     Ret
    0.08
    Activations Density 0.101%

    No Known Activations