© 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. 49115
    Prev
    Next
    INDEX
    Explanations

    HEADER, church nave, adrenaline

    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
    éĥ½æĥ³
    -0.10
    TRS
    -0.10
    oves
    -0.09
    éļıæīĭ
    -0.09
    强度
    -0.09
    tes
    -0.08
    æ®Ĩ
    -0.08
    sed
    -0.08
    ิà¸Ļ
    -0.08
    æľī趣çļĦ
    -0.08
    POSITIVE LOGITS
    ew
    0.09
    åħ¸ç¤¼
    0.09
    emen
    0.08
    Chunks
    0.08
     Nug
    0.08
    æ¯ĽåŃĶ
    0.08
    éķ
    0.08
    纽
    0.08
    æľ¯è¯Ń
    0.08
    ema
    0.08
    Activations Density 0.001%

    No Known Activations