© 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. 20274
    Prev
    Next
    INDEX
    Explanations

    a/s/o abbreviation

    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
    bas
    -0.09
    _PLATFORM
    -0.09
    èĿ´èĿ¶
    -0.09
    brig
    -0.09
    umas
    -0.08
    干活
    -0.08
    arih
    -0.08
    hardt
    -0.08
    aye
    -0.08
    é¡¿
    -0.08
    POSITIVE LOGITS
    å¸ļ
    0.09
    åĬŀ好
    0.09
    ä¸Ģç«Ļ
    0.09
    sis
    0.08
    çİĭåŃIJ
    0.08
    ä¹ĭéģĵ
    0.08
    кÑĥÑģ
    0.08
    &A
    0.08
    FilterWhere
    0.08
    offsetof
    0.08
    Activations Density 0.157%

    No Known Activations