© 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. 10513
    Prev
    Next
    INDEX
    Explanations

    visual relating to appearance and representation

    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
    æµ£
    -0.09
    ä½ĵä¼ļåĪ°
    -0.08
    ownt
    -0.08
    éĢ
    -0.08
    /job
    -0.08
    icket
    -0.08
    å°¼æĸ¯
    -0.08
    ubs
    -0.08
    ×Ļ׳×Ķ
    -0.08
     Osman
    -0.08
    POSITIVE LOGITS
    è§Ĩè§ī
    0.13
    .Visual
    0.12
    visual
    0.11
    Visual
    0.10
    .visual
    0.10
     visually
    0.09
    壮è§Ĥ
    0.09
    形象
    0.09
    (vis
    0.09
    åĥıæĺ¯
    0.09
    Activations Density 0.061%

    No Known Activations