© 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. 63359
    Prev
    Next
    INDEX
    Explanations

    evolutionary concepts

    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
    å®ŀåĬ¡
    -0.10
    æĿĸ
    -0.09
    -bars
    -0.09
    koa
    -0.09
    åľ¨ä¸ĢæĹģ
    -0.09
     translucent
    -0.09
    èĥĮçĿĢ
    -0.08
    å®ŀéĻħæݧåĪ¶
    -0.08
    饶
    -0.08
    éĢıæĺİ
    -0.08
    POSITIVE LOGITS
    è¿ĽåĮĸ
    0.15
     Cres
    0.12
    è¾¾å°Ķ
    0.10
     Evolution
    0.10
     Darwin
    0.10
     evolutionary
    0.09
    lops
    0.09
    кÑĥÑģ
    0.09
    天èµĭ
    0.09
     Duel
    0.09
    Activations Density 0.026%

    No Known Activations