© 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. 53856
    Prev
    Next
    INDEX
    Explanations

    delete, erase, delete, erase

    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
    èĥ¥
    -0.10
     reserved
    -0.10
    Reserved
    -0.10
     Reserved
    -0.09
    APA
    -0.09
    oman
    -0.09
    _reload
    -0.09
    éªģ
    -0.08
     RESERVED
    -0.08
    edelta
    -0.08
    POSITIVE LOGITS
    ä¿Ŀå¯Ĩ
    0.13
    éĶĢæ¯ģ
    0.13
    æij§æ¯ģ
    0.11
    æ³Ħ
    0.11
    æķıæĦŁ
    0.10
    åįģæĿ¡
    0.10
    ä¿¡æģ¯å®īåħ¨
    0.10
    æįIJ
    0.09
    æ¯ģçģŃ
    0.09
    å¤ļå±Ĥ次
    0.09
    Activations Density 0.043%

    No Known Activations