© 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. 38745
    Prev
    Next
    INDEX
    Explanations

    fabric, ingredients, yarn, mix

    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
    scopes
    -0.09
    åķľ
    -0.09
    åıĮ
    -0.08
    /on
    -0.08
    å½¼æѤ
    -0.08
    åľ³
    -0.08
    åħ¢
    -0.08
    æĭį
    -0.08
    ä½łçŁ¥éģĵ
    -0.08
    ikal
    -0.08
    POSITIVE LOGITS
    褶
    0.10
    ç¼ĸç»ĩ
    0.10
    èĶĵ
    0.10
    è¿·ä¿¡
    0.09
    ç»ĩ
    0.09
    threads
    0.09
    éĵ§
    0.09
    åĩºåı°äºĨ
    0.09
     fabric
    0.09
    Ľå»º
    0.09
    Activations Density 0.020%

    No Known Activations