© 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. 30111
    Prev
    Next
    INDEX
    Explanations

    numbers including negative values

    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
    stüt
    -0.10
    ssi
    -0.09
    ÐIJÐĿ
    -0.09
    uci
    -0.09
    جب
    -0.09
    avra
    -0.09
    InOut
    -0.08
    Õ³
    -0.08
    APON
    -0.08
    ç¢ĵ
    -0.08
    POSITIVE LOGITS
    人
    0.11
    s
    0.10
    o
    0.10
    issing
    0.10
    orary
    0.10
    è¿ĻèĪ¬
    0.10
    asley
    0.09
    éĩįçĤ¹é¢ĨåŁŁ
    0.09
    er
    0.09
    most
    0.09
    Activations Density 0.486%

    No Known Activations