© 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. 17274
    Prev
    Next
    INDEX
    Explanations

    scores and leads

    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
     ÑĢож
    -0.09
    ä¸Ģéĺµ
    -0.09
    BOSE
    -0.09
    御
    -0.09
    æľīä»»ä½ķ
    -0.09
    æĶ¶ç´§
    -0.09
    æľī人
    -0.08
    ä»»ä½ķ人
    -0.08
    اÛĮ
    -0.08
    åĪ¶æľį
    -0.08
    POSITIVE LOGITS
    主æĮģåı¬å¼Ģ
    0.09
    åĦĴ
    0.09
     воÑģ
    0.08
    forecast
    0.08
    ØŃÙĪ
    0.08
    LU
    0.08
    æ·
    0.08
    为æĪij们
    0.08
    .restore
    0.08
    çĿ£
    0.08
    Activations Density 0.025%

    No Known Activations