© 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. 19329
    Prev
    Next
    INDEX
    Explanations

    energy and its relations

    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
    _uv
    -0.09
    eger
    -0.09
    енко
    -0.09
    çľ¼ä¸ĭ
    -0.09
    aring
    -0.08
    éĢį
    -0.08
    çľ¼éĩĮ
    -0.08
     UV
    -0.08
    ç»ıéªĮ丰å¯Į
    -0.08
    uv
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.12
    åħħæ²Ľ
    0.12
    åĴĮæĬĢæľ¯
    0.11
    罩
    0.11
    ç²¾åĬĽ
    0.10
    ç¿»å¼Ģ
    0.09
    æĹºçĽĽ
    0.09
     bÃłn
    0.09
     MIS
    0.09
    sim
    0.09
    Activations Density 0.006%

    No Known Activations