© 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. 19320
    Prev
    Next
    INDEX
    Explanations

    historical records

    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
     yacht
    -0.11
    è§ģè¯ģäºĨ
    -0.10
    çĩİ
    -0.09
    ripp
    -0.08
    sess
    -0.08
    æĬŁ
    -0.08
    rames
    -0.08
    çħ¨
    -0.08
    æĹłæĥħ
    -0.08
    åħ¨çIJĥæľĢ大
    -0.08
    POSITIVE LOGITS
    诮
    0.08
    ÙĪص
    0.08
    åĺī
    0.08
    æIJ¬è¿ģ
    0.08
    guid
    0.08
    ä¸įå¦Ĥ
    0.08
    åİħ
    0.08
    ussy
    0.08
    ara
    0.08
    èĶĵ
    0.07
    Activations Density 0.018%

    No Known Activations