© 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. 9713
    Prev
    Next
    INDEX
    Explanations

    called in, called up

    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
    èĩªåľ¨
    -0.11
    æĪĸå¤ļ
    -0.10
    ieve
    -0.09
    æ¼Ķ
    -0.09
    åı¤åħ¸
    -0.09
     Hind
    -0.09
    票
    -0.09
    俯
    -0.09
    é¹ŀ
    -0.08
    ilater
    -0.08
    POSITIVE LOGITS
    ãģ£
    0.09
    é£İå°ļ
    0.09
    åĩºå±Ģ
    0.08
    æİĩ
    0.08
    èĭ
    0.08
    ä¸ľæµ·
    0.08
    çł
    0.08
    çŃīè¡Įä¸ļ
    0.08
    åı®åĺ±
    0.08
    çļĦåij½è¿IJ
    0.08
    Activations Density 0.021%

    No Known Activations