© 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. 56943
    Prev
    Next
    INDEX
    Explanations

    free with purchase

    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
    .ci
    -0.10
    åIJĦè¡Į
    -0.09
    PIP
    -0.09
     Courier
    -0.08
    èĵĵ
    -0.08
    agar
    -0.08
    è¯Ħè®®
    -0.08
    зÑĭ
    -0.08
    æĪĽ
    -0.08
    大å®Ĺ
    -0.08
    POSITIVE LOGITS
    åħįè´¹
    0.09
    acle
    0.09
    éĻIJéĩı
    0.09
     gratis
    0.09
    èĩªå·±åĸľæ¬¢
    0.09
     беÑģплаÑĤно
    0.09
    bundle
    0.09
     무ë£Į
    0.09
    åħ¥åĽŃ
    0.09
    è¶ħé¢Ŀ
    0.08
    Activations Density 0.086%

    No Known Activations