© 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. 4387
    Prev
    Next
    INDEX
    Explanations

    `.blog` or `.com` endings

    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
    isma
    -0.10
    gress
    -0.10
    è¡£
    -0.09
    ä¸įæĩĪ
    -0.08
    chk
    -0.08
    argon
    -0.08
    ç±į
    -0.08
    guess
    -0.08
     Bros
    -0.08
    é²ĩ
    -0.08
    POSITIVE LOGITS
    ç¿
    0.09
    åĨĴçĿĢ
    0.09
    è½»
    0.09
     setC
    0.09
    lemen
    0.08
    æ³Ľ
    0.08
    åĨĴ
    0.08
    å¿Ŀ
    0.08
    _hop
    0.08
    髯
    0.08
    Activations Density 0.153%

    No Known Activations