© 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. 35320
    Prev
    Next
    INDEX
    Explanations

    FILED/filed followed by date or context

    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
    KB
    -0.08
    饴
    -0.08
     gist
    -0.07
    datum
    -0.07
    برÙĬ
    -0.07
     pam
    -0.07
    è¿ĽèĢĮ
    -0.07
    пÑĭ
    -0.07
    -txt
    -0.07
     Spar
    -0.07
    POSITIVE LOGITS
    ately
    0.13
    ç©į
    0.10
    èĢĮæĿ¥
    0.10
    è¾ķ
    0.09
    anken
    0.09
    erate
    0.09
     недо
    0.09
    razil
    0.09
    å·²ç»ı被
    0.09
    åĻ¼
    0.09
    Activations Density 0.023%

    No Known Activations