© 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. 52848
    Prev
    Next
    INDEX
    Explanations

    pass something 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
    亿åIJ¨
    -0.09
    aces
    -0.09
    pectrum
    -0.09
    bounding
    -0.09
    _MAGIC
    -0.09
     поÑĤеÑĢ
    -0.08
    imed
    -0.08
    пÑĥÑĤ
    -0.08
    ç§ģä¸ĭ
    -0.08
    habit
    -0.08
    POSITIVE LOGITS
     muster
    0.12
    éļ¾åħ³
    0.11
     passed
    0.10
    (pass
    0.10
     Passing
    0.09
     Passed
    0.09
    ively
    0.09
    èĢĥéªĮ
    0.09
    ä¸įéĢļ
    0.09
    æīĭä¸ŃçļĦ
    0.09
    Activations Density 0.102%

    No Known Activations