© 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. 17615
    Prev
    Next
    INDEX
    Explanations

    subset of

    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
    头æĿ¡
    -0.09
    åı²ä¸Ĭ
    -0.09
    没éĶĻ
    -0.08
    angible
    -0.08
    ä»ĺãģij
    -0.08
    addafi
    -0.08
    åĵĤ
    -0.08
    åĻ±
    -0.08
    è¿ĻåIJį
    -0.08
    urve
    -0.08
    POSITIVE LOGITS
    subset
    0.10
     subset
    0.10
    ä¹ĥèĩ³
    0.09
    ç²¹
    0.09
    åī¥ç¦»
    0.08
    _subset
    0.08
    çIJĨäºĭ
    0.08
     vows
    0.08
     Williamson
    0.08
     Subset
    0.08
    Activations Density 0.072%

    No Known Activations