© 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. 2164
    Prev
    Next
    INDEX
    Explanations

    learning and assessment resources

    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
    æīĭä¸ŃçļĦ
    -0.11
    榫
    -0.10
    _bridge
    -0.10
    æĻķ
    -0.10
    æ±Łå±±
    -0.10
    ainter
    -0.10
     agency
    -0.09
    isia
    -0.09
     Ethan
    -0.09
    -lang
    -0.09
    POSITIVE LOGITS
    éħįå¤ĩ
    0.10
    æѦè£ħ
    0.09
    订
    0.08
    订è´Ń
    0.08
    认åIJĮ
    0.08
    ayo
    0.08
     ÑĦонд
    0.08
     retro
    0.08
    æ¶İ
    0.08
    çĭŃ
    0.08
    Activations Density 0.025%

    No Known Activations