© 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. 3913
    Prev
    Next
    INDEX
    Explanations

    stain or spill cleaning

    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
    éĢłç¦ı
    -0.11
    å±±åİ¿
    -0.10
    çļĦæĥħ绪
    -0.10
    иÑĢованиÑı
    -0.09
    (OP
    -0.09
    çĺ¾
    -0.09
    ç²½
    -0.09
    æĭĮ
    -0.09
    _OP
    -0.09
     Mine
    -0.09
    POSITIVE LOGITS
    mark
    0.09
    æ°¸ä¹ħ
    0.09
     wine
    0.08
    顽
    0.08
    wine
    0.08
    chalk
    0.08
    COORD
    0.08
    ä¸į太
    0.08
    ä½ı
    0.08
    åĿIJ
    0.08
    Activations Density 0.045%

    No Known Activations