© 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. 55110
    Prev
    Next
    INDEX
    Explanations

    emanate / radiate

    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
    lift
    -0.09
    ç»Į
    -0.09
    çļĦåĪ°æĿ¥
    -0.08
    òn
    -0.08
    ton
    -0.08
     Somalia
    -0.08
    _EXIST
    -0.08
     EXPORT
    -0.08
    æīĺè¿IJ
    -0.08
    åħ¨éĿ¢åıijå±ķ
    -0.08
    POSITIVE LOGITS
    çĿĢ
    0.10
    åģļ个
    0.09
    HAL
    0.09
    kat
    0.09
    èĩªä¿¡
    0.09
    åĩºåİ»
    0.08
    ively
    0.08
    çĨŁ
    0.08
    缱
    0.08
    apl
    0.08
    Activations Density 0.008%

    No Known Activations