© 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. 61240
    Prev
    Next
    INDEX
    Explanations

    polytetrafluoroethylene, non-slip, static bag

    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
    ettes
    -0.09
    elor
    -0.09
    aur
    -0.09
    ä½ľçĶ¨
    -0.09
    aq
    -0.08
    严谨
    -0.08
    åIJijåīį
    -0.08
    -selector
    -0.08
    使çĶ¨èĢħ
    -0.08
    aqu
    -0.08
    POSITIVE LOGITS
    subst
    0.09
    ç®Ķ
    0.09
    æªĦ
    0.09
    enty
    0.09
    è¿Ļå¥Ĺ
    0.08
    è¸Ĭ
    0.08
    身躯
    0.08
    éĹ»
    0.08
    .assignment
    0.08
    reen
    0.08
    Activations Density 0.001%

    No Known Activations