© 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. 17325
    Prev
    Next
    INDEX
    Explanations

    knitting and crochetcrafts

    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¿ĻçĿĢ
    -0.11
    coni
    -0.09
    \$
    -0.09
    ç«Ļç«ĭ
    -0.08
    æįĨ
    -0.08
    ances
    -0.08
    inoa
    -0.08
    éc
    -0.08
    Washington
    -0.08
     bl
    -0.08
    POSITIVE LOGITS
    iffs
    0.10
    èĢĮæĪIJ
    0.09
    elman
    0.09
    ings
    0.09
    ä»İæł¹æľ¬ä¸Ĭ
    0.09
    åįģæľĪ
    0.09
    ê¹IJ
    0.09
    åľ¨ä¸Ģèµ·
    0.09
    ongs
    0.09
    èĻ±
    0.09
    Activations Density 0.006%

    No Known Activations