© 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. 11719
    Prev
    Next
    INDEX
    Explanations

    animals and nature

    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
    éĻ²
    -0.10
    æµģåĬ¨æĢ§
    -0.10
    kaar
    -0.10
    溺
    -0.10
    è¾Ī
    -0.09
    å¤§éĽ¨
    -0.09
    _Double
    -0.09
    å¢ģ
    -0.09
    ension
    -0.09
    é£ŀæī¬
    -0.09
    POSITIVE LOGITS
    æłij
    0.11
     tree
    0.09
    é¸
    0.08
    åĵģç§į
    0.08
    å²Ń
    0.08
    æŁ³
    0.08
    /framework
    0.08
    è¡«
    0.08
    èĢĥéĩı
    0.08
    ampus
    0.08
    Activations Density 0.263%

    No Known Activations