© 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. 21646
    Prev
    Next
    INDEX
    Explanations

    scores and results

    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
    sted
    -0.09
    è¿ĽæĿ¥
    -0.08
    sl
    -0.08
    çĹĺ
    -0.08
    öm
    -0.08
    çĸ³
    -0.08
    缴åĪ°
    -0.08
    oom
    -0.08
    ç«¿
    -0.08
     until
    -0.08
    POSITIVE LOGITS
    æľīæĿ¡ä»¶çļĦ
    0.10
    æľīæĿ¡ä»¶
    0.10
     Zur
    0.09
    åĪĽåĬŀ
    0.09
    åĪĨæīĭ
    0.09
    .websocket
    0.09
    æŀ£
    0.09
    侧
    0.09
    æ¯ĶåĪĨ
    0.08
    APPER
    0.08
    Activations Density 0.068%

    No Known Activations