© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22058
    Prev
    Next
    INDEX
    Explanations

    wound, wrapped, reels

    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
    acement
    -0.10
    å¥ij
    -0.09
    _NC
    -0.09
    æŃ£å¤Ħäºİ
    -0.09
     upside
    -0.08
    å·§
    -0.08
    æ³
    -0.08
    å¸ķ
    -0.08
    æ¥Ķ
    -0.08
    ittel
    -0.08
    POSITIVE LOGITS
    REW
    0.10
    ental
    0.10
     reel
    0.09
     slack
    0.09
    è·ijäºĨ
    0.09
     иÑģÑĤ
    0.09
    å¾ĢåIJİ
    0.09
     reels
    0.09
    éĶ¡
    0.09
    otron
    0.09
    Activations Density 0.114%

    No Known Activations