© 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. 32140
    Prev
    Next
    INDEX
    Explanations

    sinking, sank, sunk

    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
    бой
    -0.09
    ildo
    -0.08
     trụ
    -0.08
    pora
    -0.08
    hire
    -0.08
    SUR
    -0.08
    inance
    -0.08
    ระ
    -0.08
    éĥijéĩį
    -0.08
    ä½ľåĵģåĨħ容
    -0.08
    POSITIVE LOGITS
    fall
    0.10
    ç¥ī
    0.10
    ä¸ĭåİ»
    0.10
    æ²ī
    0.10
    erset
    0.09
    æ¹İ
    0.09
    yards
    0.09
    raph
    0.09
     sunk
    0.08
    holes
    0.08
    Activations Density 0.009%

    No Known Activations