© 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. 5341
    Prev
    Next
    INDEX
    Explanations

    .S. followed by period

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.11
    aina
    -0.10
    èĩ³åħ³
    -0.09
    ISION
    -0.09
     aforementioned
    -0.09
    娱
    -0.08
    å¿ĥåĬ¨
    -0.08
    afia
    -0.08
     nonzero
    -0.08
    æľĢ主è¦ģçļĦ
    -0.08
    POSITIVE LOGITS
    0.11
     ØŃÙĪ
    0.09
    OperationException
    0.09
    ï¸ı
    0.09
    สว
    0.09
    nbsp
    0.09
    errupted
    0.09
    å§Ķç»Ħç»ĩéĥ¨
    0.09
    ielding
    0.09
    VEC
    0.09
    Activations Density 0.122%

    No Known Activations