© 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. 4610
    Prev
    Next
    INDEX
    Explanations

    dates and URLs

    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
    NESS
    -0.10
    _PROP
    -0.08
     Chim
    -0.08
    ä¹ŀ
    -0.08
    ä¹ĭç¾İ
    -0.08
    ipsis
    -0.08
    ollipop
    -0.08
    ÑĦон
    -0.08
    lander
    -0.08
    oret
    -0.08
    POSITIVE LOGITS
    为åħ¶
    0.11
    åħ¶æīĢ
    0.10
    该æĢİä¹ĪåĬŀ
    0.09
    æĢİä¹ĪåĬŀ
    0.09
    è¾Ī
    0.09
    çħĬ
    0.08
    æĸ©èİ·
    0.08
    éģIJ
    0.08
    åŀ
    0.08
    amel
    0.08
    Activations Density 0.528%

    No Known Activations