© 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. 23771
    Prev
    Next
    INDEX
    Explanations

    local-class

    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
    å¸ĤåĢ¼
    -0.09
    èĦĤ
    -0.09
    å¡Ķ
    -0.09
    ìĭľ
    -0.09
    平淡
    -0.08
    ä¿Ń
    -0.08
    åĽŀå¿Ĩ
    -0.08
    åĸ»
    -0.08
    LESS
    -0.08
    è°ı
    -0.08
    POSITIVE LOGITS
    ä¹¡åľŁ
    0.10
    éĥ¢
    0.09
    å®Įæķ´æĢ§
    0.09
    ir
    0.09
    ProcAddress
    0.09
    èĦı
    0.09
    eut
    0.08
    úb
    0.08
    irie
    0.08
    åľºåľ°
    0.08
    Activations Density 0.111%

    No Known Activations