© 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. 39208
    Prev
    Next
    INDEX
    Explanations

    atar acts

    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
     Stall
    -0.10
    åĢº
    -0.09
    羣çĪ±
    -0.08
    .lastIndexOf
    -0.08
    å¤ĩ
    -0.08
    大ä¼Ĺ
    -0.08
    åĪ¨
    -0.08
    ount
    -0.08
    èĿ
    -0.08
    htdocs
    -0.08
    POSITIVE LOGITS
    èģª
    0.10
    sen
    0.10
    ld
    0.09
    èĢģå¸Ī们
    0.09
    waters
    0.09
    èģ
    0.08
    ÑĨеп
    0.08
    иÑĤа
    0.08
    åħ³éŨ
    0.08
    mux
    0.08
    Activations Density 0.061%

    No Known Activations