© 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. 57729
    Prev
    Next
    INDEX
    Explanations

    dream or vision

    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
     пÑĢÑı
    -0.10
    æ´µ
    -0.09
    emon
    -0.09
    gesture
    -0.09
    æĪ¡
    -0.09
    é¢Ĩ
    -0.08
    æķ¬ä¸ļ
    -0.08
    æĺ¯ä¸įåı¯èĥ½
    -0.08
    esse
    -0.08
     sounding
    -0.08
    POSITIVE LOGITS
    ãĥĵãĤ¸
    0.11
    涯
    0.10
    å±ķæľĽ
    0.09
     vision
    0.09
    å¾Īæ·±
    0.09
     visions
    0.09
    éĴī
    0.09
    çķĢ
    0.09
    èŃ¦ç¤º
    0.09
    æŀķ头
    0.09
    Activations Density 0.044%

    No Known Activations