© 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. 56298
    Prev
    Next
    INDEX
    Explanations

    approaching soon

    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
    çŁ³åĮĸ
    -0.10
    èĨı
    -0.10
    é¦Ĩ
    -0.10
    åģļåĪ°äºĨ
    -0.10
     minY
    -0.09
     lud
    -0.09
    è¿Ļè¾ĪåŃIJ
    -0.09
    çĸı导
    -0.09
    osti
    -0.08
    ä¸ŃåĽ½å¸Ĥåľº
    -0.08
    POSITIVE LOGITS
    åį³å°ĨåĪ°æĿ¥
    0.11
    ä¸įè¿ľ
    0.10
    è¶ĬæĿ¥
    0.10
    ãģ¾ãģĹãģ¦
    0.09
    æµ·å°Ķ
    0.09
    è¿«ä¸įåıĬå¾ħ
    0.09
     imminent
    0.09
     ÑģкоÑĢо
    0.09
    åį³å°Ĩ
    0.09
    preced
    0.09
    Activations Density 0.037%

    No Known Activations