© 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. 31413
    Prev
    Next
    INDEX
    Explanations

    canine, feline, piggybacking

    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
    sWith
    -0.11
    maker
    -0.11
    家人
    -0.09
    æĤ£
    -0.09
    ç§į
    -0.09
    allis
    -0.09
    iane
    -0.09
    lify
    -0.08
    croft
    -0.08
    ãģĵãģ¨ãĤĴ
    -0.08
    POSITIVE LOGITS
    çĽĽå®´
    0.10
    ester
    0.10
    说çļĦæĺ¯
    0.09
    arie
    0.09
    agn
    0.09
    çĶľçĶľ
    0.09
    _opts
    0.08
    tain
    0.08
    ç²¾åįİ
    0.08
    ize
    0.08
    Activations Density 0.007%

    No Known Activations