© 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. 1261
    Prev
    Next
    INDEX
    Explanations

    alloy or blend

    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
    åİ»è¿ĩ
    -0.09
    å¡į
    -0.09
    èĴ¸
    -0.09
    uki
    -0.09
    DOM
    -0.08
    ึà¸ģ
    -0.08
     Bott
    -0.08
     DOM
    -0.08
    .binding
    -0.08
    èľ·
    -0.08
    POSITIVE LOGITS
    åIJĪéĩij
    0.15
     alloy
    0.13
    æĪIJåĪĨ
    0.12
    blend
    0.12
     alloys
    0.11
     blend
    0.11
    亲
    0.11
    Blend
    0.10
     Blend
    0.10
    плав
    0.10
    Activations Density 0.238%

    No Known Activations