© 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. 33882
    Prev
    Next
    INDEX
    Explanations

    tax obligations

    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
    ness
    -0.10
    ç¢į
    -0.09
    scale
    -0.09
    sp
    -0.09
    强èĢħ
    -0.08
    åĬ²
    -0.08
    spe
    -0.08
    ers
    -0.08
     dame
    -0.08
    acie
    -0.08
    POSITIVE LOGITS
    gens
    0.11
    åĩºå±Ģ
    0.09
    æĪ·åı£
    0.09
    èı¡
    0.09
    anko
    0.09
    å¥Ħ
    0.09
    лÑĮ
    0.09
    rès
    0.09
    æĪ¿ç§Ł
    0.09
    æĿŀ
    0.09
    Activations Density 0.012%

    No Known Activations