© 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. 6415
    Prev
    Next
    INDEX
    Explanations

    but WITHOUT

    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¸įä½Ĩ
    -0.13
    åĽºçĦ¶
    -0.13
    èĢĮåİ»
    -0.11
     denn
    -0.11
    à¸Ļำ
    -0.10
    æīĢ以ä»ĸ
    -0.10
    äºİæĺ¯
    -0.10
    ãģĿãģĹãģ¦
    -0.10
    -0.10
    èĢĮä¸Ķ
    -0.10
    POSITIVE LOGITS
    ted
    0.12
    chers
    0.12
    ting
    0.12
    /of
    0.11
     ×ķרק
    0.10
    ters
    0.09
    ts
    0.09
    ä»įæľī
    0.09
    说æĺ¯
    0.09
    ane
    0.09
    Activations Density 0.217%

    No Known Activations