© 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. 53641
    Prev
    Next
    INDEX
    Explanations

    .pt suffix

    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
    åľ¨åħ¨åĽ½
    -0.10
    åľ¨ç¾İåĽ½
    -0.10
    åIJĮåŁİ
    -0.09
    æİĸ
    -0.09
    trak
    -0.09
     Nationwide
    -0.09
    åĽ½äº§
    -0.09
    åĽ½æĥħ
    -0.08
    åĽłä¸ºä»ĸ们
    -0.08
    缮åīįåĽ½åĨħ
    -0.08
    POSITIVE LOGITS
     FIFA
    0.09
    åīį
    0.09
    opers
    0.08
    essed
    0.08
    ãģĹãĤĩãģĨ
    0.08
    åĽ½éĻħå¸Ĥåľº
    0.08
    arse
    0.08
    igu
    0.08
     moc
    0.08
    EU
    0.08
    Activations Density 0.320%

    No Known Activations