© 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. 3460
    Prev
    Next
    INDEX
    Explanations

    patches, stickers, posters, paperback

    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
    å¯ĵ
    -0.10
     RTS
    -0.09
    çĸı导
    -0.09
    çªĸ
    -0.09
    Pitch
    -0.09
    ç¬ŀ
    -0.09
    estro
    -0.09
    imedia
    -0.08
    æµģæĺŁ
    -0.08
     slashed
    -0.08
    POSITIVE LOGITS
    çķĻ
    0.10
    çķĻä¸ĭ
    0.09
    æĶĴ
    0.09
    çķĻä¸ĭäºĨ
    0.09
    çĪ°
    0.09
    ä¿Ŀåģ¥
    0.08
    涣
    0.08
    ãĤ¦ãĥ³
    0.08
    çķĻä¸ĭæĿ¥
    0.08
    åı¯éĿłçļĦ
    0.08
    Activations Density 0.149%

    No Known Activations