© 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. 27553
    Prev
    Next
    INDEX
    Explanations

    percentage

    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
    ink
    -0.08
    åİŁæłĩé¢ĺ
    -0.08
    寡
    -0.08
    è¿Ķ乡
    -0.08
    æĺŁæľŁ
    -0.07
     Enum
    -0.07
     zones
    -0.07
    å½ĵçĦ¶æĺ¯
    -0.07
    alysis
    -0.07
     Buyer
    -0.07
    POSITIVE LOGITS
    æ¯ıå¹´
    0.14
    åľ¨æĪijåĽ½
    0.12
    æ¯ıå¹´éĥ½
    0.11
    æĪijåĽ½
    0.11
    åĽ½äºº
    0.10
    åĮĹç¾İ
    0.10
    æĺ¯æĪijåĽ½
    0.10
    atables
    0.10
    ç¾İåĽ½äºº
    0.10
    éłĨ
    0.09
    Activations Density 0.400%

    No Known Activations