© 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. 35093
    Prev
    Next
    INDEX
    Explanations

    cuffs

    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
    éĻIJ度
    -0.10
    æľīåºı
    -0.10
    ously
    -0.10
    éĤº
    -0.09
    å¤ĸåĩº
    -0.09
    bilt
    -0.09
    å®ľå±ħ
    -0.09
    確ãģĭ
    -0.09
    ึà¸ĩ
    -0.09
    HLT
    -0.09
    POSITIVE LOGITS
    sets
    0.12
    rent
    0.10
    sWith
    0.09
    liner
    0.09
    è¢ĸ
    0.09
    çĴĺ
    0.08
     наÑĢ
    0.08
     miss
    0.08
    STREAM
    0.08
    switch
    0.08
    Activations Density 0.002%

    No Known Activations