© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7308
    Prev
    Next
    INDEX
    Explanations

    game time spans

    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
    ä¸ĸéĹ´
    -0.10
    iani
    -0.09
    ened
    -0.09
    ç³ľ
    -0.09
    arel
    -0.09
    å¹´æĿ¥
    -0.09
    _WM
    -0.09
    quential
    -0.09
    裾
    -0.09
    声éģĵ
    -0.08
    POSITIVE LOGITS
    ãĥ¼ãĤ·
    0.09
    åıijçİ°èĩªå·±
    0.09
    æŃ£å½ĵ
    0.09
    æĸĩåĮĸä¼łæĴŃ
    0.09
    亲çĪ±
    0.08
    çļĦåľ°
    0.08
    -middle
    0.08
     rej
    0.08
    á»Ĺ
    0.08
    å·¥ä½ľæĬ¥åijĬ
    0.08
    Activations Density 0.028%

    No Known Activations