© 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. 56648
    Prev
    Next
    INDEX
    Explanations

    adding to

    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
    åĩºåİĤ
    -0.10
    ochen
    -0.10
    OTO
    -0.09
     اÙĦØ£ÙĨ
    -0.09
    缸æ¯Ķä¹ĭä¸ĭ
    -0.09
    .intent
    -0.09
    rios
    -0.09
    çªģçł´åı£
    -0.09
    uien
    -0.09
    awl
    -0.09
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJ
    0.09
    åĽ°æī°
    0.09
    认è¯Ĩ
    0.08
    ../../../
    0.08
    çīĿ
    0.08
    äºĭä¸ļåıijå±ķ
    0.08
    èĢĮéĿŀ
    0.08
    æĪijçĽ¸ä¿¡
    0.08
    çļĦåĬ¨åĬĽ
    0.08
    erview
    0.08
    Activations Density 0.017%

    No Known Activations