© 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. 7392
    Prev
    Next
    INDEX
    Explanations

    continue to remain

    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»İæĿ¥
    -0.10
    åİĨæĿ¥
    -0.09
    ÑĢÑĥж
    -0.09
    TZ
    -0.08
    iales
    -0.08
    ä»İæĿ¥æ²¡æľī
    -0.08
    èĩªæĿ¥
    -0.08
    赦
    -0.08
    æ´ĭèij±
    -0.08
    .codes
    -0.08
    POSITIVE LOGITS
    asm
    0.09
    رات
    0.09
    -secondary
    0.09
    èĮ¬
    0.09
     secondary
    0.09
    essen
    0.08
    äºĮ级
    0.08
    adier
    0.08
    麻çĹ¹
    0.08
    Ñĥй
    0.08
    Activations Density 0.117%

    No Known Activations