© 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. 2898
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    æĻ¯å¾·
    -0.09
    å°ıäºĭ
    -0.09
    èĩªæľī
    -0.09
    abbit
    -0.09
    èĪĴéĢĤçļĦ
    -0.09
    èĪĴéĢĤ
    -0.09
    åĨĽå®ĺ
    -0.09
    天空
    -0.09
    çĪ±æĬ¤
    -0.08
    èĮ¹
    -0.08
    POSITIVE LOGITS
    ech
    0.08
    SPA
    0.08
    èĥ¸
    0.08
    een
    0.08
     Nelson
    0.08
    ç±į
    0.07
    éĤ¯
    0.07
    举éĥ¨
    0.07
    åĬ©çIJĨ
    0.07
    egan
    0.07
    Activations Density 0.318%

    No Known Activations