© 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. 58853
    Prev
    Next
    INDEX
    Explanations

    star or stars

    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
    ester
    -0.10
    atron
    -0.09
    orent
    -0.09
    DateString
    -0.09
    çĿ¬
    -0.09
    enders
    -0.09
    esa
    -0.09
    standing
    -0.09
    umo
    -0.09
    家ä¼Ļ
    -0.09
    POSITIVE LOGITS
    burst
    0.12
    ategy
    0.11
    otle
    0.10
    light
    0.10
    lights
    0.10
    纬
    0.09
    ved
    0.09
    å®ķ
    0.09
    bucks
    0.09
    箸
    0.09
    Activations Density 0.035%

    No Known Activations