© 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. 8490
    Prev
    Next
    INDEX
    Explanations

    names, often followed by punctuation

    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
    anke
    -0.10
    羣çIJĨ
    -0.09
    lico
    -0.08
    èĢĻ
    -0.08
    æѤäºĭ
    -0.08
    DoubleClick
    -0.08
    跻身
    -0.08
    å¼¹
    -0.08
    /security
    -0.08
    æ¯Ľå·¾
    -0.08
    POSITIVE LOGITS
    è¶³å¤Ł
    0.10
    åĨ°ç®±
    0.09
    å´ĩé«ĺ
    0.09
    /fixtures
    0.08
     tst
    0.08
    uxe
    0.08
    SEL
    0.08
    æĿ¥å®¾
    0.08
    andle
    0.08
    åĵ¥
    0.08
    Activations Density 0.001%

    No Known Activations