© 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. 30584
    Prev
    Next
    INDEX
    Explanations

    start of phrase/sentence

    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
    _Impl
    -0.08
    нÑĮ
    -0.08
    æł¸æŁ¥
    -0.08
     questioning
    -0.08
    Ø¡
    -0.08
    离
    -0.07
    راء
    -0.07
    ä»ĸ们
    -0.07
     wor
    -0.07
    éĹ¹
    -0.07
    POSITIVE LOGITS
    æĪijè¦ģ
    0.13
    æĢĿ绪
    0.12
    åĽłä¸ºæĪij
    0.11
    å°Ĩ以
    0.11
    ä¹Łä¸įæĥ³
    0.10
    åĨĻä¸ĭ
    0.10
    /twitter
    0.10
    çļĦæĦ¿æľĽ
    0.10
    æĬ¢
    0.10
    æĪijä¸įæĥ³
    0.10
    Activations Density 0.150%

    No Known Activations