© 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. 5214
    Prev
    Next
    INDEX
    Explanations

    Championship events and finals

    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
    -0.13
    onaut
    -0.11
    onomy
    -0.11
    è¿Ļå°±
    -0.10
    athon
    -0.10
    EMENT
    -0.10
    imately
    -0.09
    åºŀ大
    -0.09
    ings
    -0.09
    lessly
    -0.09
    POSITIVE LOGITS
    ci
    0.09
    nist
    0.09
     Publishers
    0.09
    cy
    0.09
    -winning
    0.09
    ëł¹
    0.09
    cial
    0.09
    reuse
    0.08
    éĺ¿éĩĮå·´å·´
    0.08
    éĢ¯
    0.08
    Activations Density 0.043%

    No Known Activations