© 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. 35257
    Prev
    Next
    INDEX
    Explanations

    photo related contexts

    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
    ustr
    -0.10
    edReader
    -0.10
    èĩ¼
    -0.09
    -0.09
     NOTICE
    -0.09
    éĨ¯
    -0.09
    urance
    -0.09
    rag
    -0.09
    ugar
    -0.08
    åķĨåѦéĻ¢
    -0.08
    POSITIVE LOGITS
    hoot
    0.17
    ynthesis
    0.12
    ะ
    0.10
    ocop
    0.10
    /video
    0.10
    opy
    0.09
    wipe
    0.09
    asso
    0.09
    æ£ļ
    0.09
    _quality
    0.09
    Activations Density 0.079%

    No Known Activations