© 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. 47782
    Prev
    Next
    INDEX
    Explanations

    Morrison

    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
    æĸ¯åŁº
    -0.11
    urer
    -0.09
     ÙħدÙī
    -0.09
     Albert
    -0.09
    ç½Ħ
    -0.09
    æģ¨
    -0.09
    æ¸į
    -0.09
    å¯ĨéĽĨ
    -0.09
    ÑĤип
    -0.08
     Ble
    -0.08
    POSITIVE LOGITS
    .nih
    0.10
    讲æķħäºĭ
    0.10
    çIJ°
    0.09
    ears
    0.09
    icks
    0.09
    xl
    0.08
    _ck
    0.08
    ents
    0.08
    ption
    0.08
    çĪµ
    0.08
    Activations Density 0.005%

    No Known Activations