© 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. 34647
    Prev
    Next
    INDEX
    Explanations

    shipping locations or services

    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
    è¿ĺæľīä»Ģä¹Ī
    -0.09
    忽çĦ¶
    -0.09
    peat
    -0.09
    åĶ±
    -0.09
    è¿ĺæľī
    -0.08
    (exports
    -0.08
    å¼Ħ
    -0.08
    Ñıн
    -0.08
    èĩªæķij
    -0.08
    士
    -0.08
    POSITIVE LOGITS
    ä¸įä½İäºİ
    0.13
    æľĢåħĪè¿ĽçļĦ
    0.12
    éĢĤ度
    0.11
    èĢĮä¸įæĺ¯
    0.10
    æľĢéĢĤåIJĪ
    0.10
    å±ĬæŶ
    0.10
    å½ĵåľ°çļĦ
    0.10
    æĸ¹å¼ıè¿Ľè¡Į
    0.10
     either
    0.10
    å°½åı¯èĥ½
    0.10
    Activations Density 0.296%

    No Known Activations