© 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. 48804
    Prev
    Next
    INDEX
    Explanations

    liable for / to

    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
    uman
    -0.09
    onest
    -0.08
    ses
    -0.08
    å·¢
    -0.08
    é«ĺ强度
    -0.08
    obl
    -0.08
    sing
    -0.07
    ÑĢок
    -0.07
    pir
    -0.07
    æĭ¯
    -0.07
    POSITIVE LOGITS
    é¢ł
    0.10
    é¦
    0.09
    æ°´æĻ¶
    0.09
    entes
    0.09
    .itemView
    0.09
    _MEDIA
    0.09
     kê
    0.09
    LING
    0.09
    _RT
    0.08
    æĨ©
    0.08
    Activations Density 0.007%

    No Known Activations