© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19599
    Prev
    Next
    INDEX
    Explanations

    because of

    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
    åıªè¦ģæľī
    -0.11
    ä¸ĢçĻ¾
    -0.10
    åĩ¡æĺ¯
    -0.10
    迨
    -0.10
    reachable
    -0.10
    èѬ
    -0.10
    ĺìĿ´
    -0.09
    çĶļèĩ³
    -0.09
    ä¸Ģåįĥ
    -0.09
    建æĪIJåIJİ
    -0.09
    POSITIVE LOGITS
    ç§įç§į
    0.10
    yan
    0.09
     its
    0.09
    ä»Ģä¹ĪåİŁåĽł
    0.09
    éĥijéĩį
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.08
    çļĦç¼ĺæķħ
    0.08
    åĩłçĤ¹
    0.08
    趾
    0.08
    ãģĵãģ¨ãģ«
    0.08
    Activations Density 0.019%

    No Known Activations