© 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. 4486
    Prev
    Next
    INDEX
    Explanations

    last followed by duration

    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
    tran
    -0.10
    ãĥ¥
    -0.09
    hill
    -0.09
    ÑģÑĤой
    -0.08
    çĶŁæĢķ
    -0.08
    ULAR
    -0.08
    å¸ĮæľĽéĢļè¿ĩ
    -0.08
    sert
    -0.08
    éļıä¹ĭ
    -0.08
    azon
    -0.08
    POSITIVE LOGITS
    ube
    0.11
    INGS
    0.10
    ä¸įæŃ¢
    0.09
    rious
    0.09
    ÅĤe
    0.09
    ä¸įä½³
    0.09
    andard
    0.09
    riet
    0.09
     Platt
    0.09
    IDI
    0.09
    Activations Density 0.008%

    No Known Activations