© 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. 2442
    Prev
    Next
    INDEX
    Explanations

    local followed by information, rules, or services

    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
    黾
    -0.10
    uers
    -0.09
    ilos
    -0.09
    ilog
    -0.08
    asers
    -0.08
    ãģıãĤĮ
    -0.08
    inel
    -0.08
    apro
    -0.08
    æ¿
    -0.08
    lang
    -0.08
    POSITIVE LOGITS
    ities
    0.17
    ized
    0.17
    ised
    0.16
    izedName
    0.15
    itÃł
    0.14
    isation
    0.13
    izable
    0.13
    ization
    0.13
    izes
    0.13
    izing
    0.13
    Activations Density 0.055%

    No Known Activations