© 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. 55459
    Prev
    Next
    INDEX
    Explanations

    All Rights Reserved

    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
    æ¯Ľ
    -0.10
    ugh
    -0.10
    管å±Ģ
    -0.10
    ellar
    -0.10
    é¸Ń
    -0.09
    tures
    -0.09
    åıªè¦ģ
    -0.09
    ãĤ¬ãĤ¤
    -0.08
    ç©°
    -0.08
    çĵ¶é¢Ī
    -0.08
    POSITIVE LOGITS
     chiếu
    0.10
    缸åĬ©
    0.10
    Spo
    0.09
    .bulk
    0.09
    å´
    0.09
    å¼Ī
    0.09
    å¹ķ
    0.08
    èĪ¬çļĦ
    0.08
    ichtig
    0.08
    æĽĻ
    0.08
    Activations Density 0.019%

    No Known Activations