© 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. 17989
    Prev
    Next
    INDEX
    Explanations

    number of shares

    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
    è´¯
    -0.11
     Eag
    -0.10
    楣
    -0.10
    模çī¹
    -0.10
    å¯Įæ°ij
    -0.10
    asio
    -0.09
    бÑĭ
    -0.09
    éo
    -0.09
    鸡èĤī
    -0.09
    èĻ¢
    -0.09
    POSITIVE LOGITS
    ừ
    0.08
    olean
    0.08
    rgan
    0.08
    NING
    0.08
     communic
    0.08
    æĭ¿
    0.08
    æİĢ
    0.08
    å¸Ĩ
    0.08
     Sap
    0.07
    /null
    0.07
    Activations Density 0.110%

    No Known Activations