© 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. 50871
    Prev
    Next
    INDEX
    Explanations

    evaluate or compare options

    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
    adle
    -0.09
    æĭĸ
    -0.09
    çļĦåľ°åĽ¾
    -0.08
    åĵģå¾·
    -0.08
    åį·
    -0.08
    Wis
    -0.08
    罩
    -0.08
    åŀĤ
    -0.08
    éĢļè¿ĩ对
    -0.08
    常
    -0.08
    POSITIVE LOGITS
    æĽ´å¥½åľ°
    0.13
    ä¸ĭä¸ĢæŃ¥
    0.10
    æľīéĴĪ对æĢ§
    0.10
    çĹĩ
    0.10
    laps
    0.10
     later
    0.09
    çŁ¥éģĵ
    0.09
    ä¸įèĩ³äºİ
    0.09
     better
    0.09
    å°±ä¸įä¼ļ
    0.09
    Activations Density 0.179%

    No Known Activations