© 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. 10661
    Prev
    Next
    INDEX
    Explanations

    to a minimum

    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
    ULD
    -0.10
    åIJijä¸Ĭ
    -0.10
    èī°èĭ¦
    -0.10
    æ¦
    -0.10
    ç½Ķ
    -0.10
    æ°´åŁŁ
    -0.09
    æ¸ħåĩī
    -0.09
    wipe
    -0.09
    è¿ĩå¾Ĺ
    -0.09
    åĪĨæĺİ
    -0.09
    POSITIVE LOGITS
     наÑĢ
    0.10
    ç²¾èĭ±
    0.10
     Pearce
    0.08
    渴
    0.08
    妥åįı
    0.08
    iani
    0.08
    åıĺæĪIJäºĨ
    0.08
     transit
    0.08
    6
    0.08
     Elite
    0.07
    Activations Density 0.174%

    No Known Activations