© 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. 18005
    Prev
    Next
    INDEX
    Explanations

    dummy or binary

    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
    lá
    -0.10
    ä¸įåIJĮç¨ĭ度
    -0.09
    ouncil
    -0.09
    indh
    -0.09
    REA
    -0.09
    obuf
    -0.09
    unner
    -0.08
    天空
    -0.08
    -Pacific
    -0.08
    ä¹ĭæĥħ
    -0.08
    POSITIVE LOGITS
    est
    0.11
    weg
    0.10
    stick
    0.10
    arton
    0.10
    ey
    0.10
    æĨ¬
    0.09
    esh
    0.09
    ards
    0.09
     luck
    0.08
    çĤ¸å¼¹
    0.08
    Activations Density 0.005%

    No Known Activations