© 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. 56818
    Prev
    Next
    INDEX
    Explanations

    guides and programming fragments

    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
    äºİæĺ¯
    -0.10
    æİĩ
    -0.10
    äºİæĺ¯æĪij
    -0.09
     hend
    -0.09
    tsy
    -0.08
    æĥ¹
    -0.08
    çĶŁç´ł
    -0.08
    çıł
    -0.08
    ushing
    -0.08
     butt
    -0.08
    POSITIVE LOGITS
    çĪ±åĽ½
    0.10
    UNC
    0.10
    Invoker
    0.09
    ä¼Łå¤§
    0.09
    æĢĴ
    0.09
    çĸ
    0.09
    åĶ®ç¥¨
    0.09
    æŁ
    0.08
     DÅ©ng
    0.08
    èĤļ
    0.08
    Activations Density 0.046%

    No Known Activations