© 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. 57309
    Prev
    Next
    INDEX
    Explanations

    front page, cover, page

    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
    ssa
    -0.09
    station
    -0.09
    å²ĺ
    -0.09
    æĺ¯ä¸ĢåIJį
    -0.08
     Hands
    -0.08
    ä¸Ĭ次
    -0.08
    Tbl
    -0.08
    stab
    -0.08
    姥
    -0.08
    髯
    -0.08
    POSITIVE LOGITS
    pling
    0.10
    侬
    0.10
    éĻĦè¿ijçļĦ
    0.10
    æĸ°éĹ»è®°èĢħ
    0.09
    寮
    0.09
    -worthy
    0.09
    çĮĽ
    0.08
    quis
    0.08
     Hogan
    0.08
    Bins
    0.08
    Activations Density 0.008%

    No Known Activations