© 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. 17985
    Prev
    Next
    INDEX
    Explanations

    oil, polymer, pharmaceutical, sand residues

    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
    tensor
    -0.10
    èĩªåľ¨
    -0.09
    ä¿ı
    -0.09
     обеÑģпеÑĩ
    -0.09
    asl
    -0.08
    æµ·çĽĹ
    -0.08
    -Dec
    -0.08
    opp
    -0.08
     rocks
    -0.08
    çľĭå¾ħ
    -0.08
    POSITIVE LOGITS
    åľ¨éĩĮéĿ¢
    0.11
    _HOR
    0.08
    ç±»
    0.08
     Wyn
    0.08
    æ®ĭçķĻ
    0.08
     Milo
    0.08
    emed
    0.08
    å¬ĸ
    0.08
    æĿ¥èĩª
    0.08
    çĺģ
    0.08
    Activations Density 0.498%

    No Known Activations