© 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. 53727
    Prev
    Next
    INDEX
    Explanations

    your information

    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
    çħ§æł·
    -0.10
    责任人
    -0.10
    äºĨèĩªå·±çļĦ
    -0.10
    为æ°ij
    -0.10
    夬
    -0.10
    å±Ģéķ¿
    -0.10
    own
    -0.10
    èĩªå·±çļĦ
    -0.10
    说èĩªå·±
    -0.10
    ä¸Ģå¼Ģå§ĭå°±
    -0.09
    POSITIVE LOGITS
    ä»Ģä¹Īä¸ľè¥¿
    0.08
    oad
    0.08
    åį¡
    0.08
    éĻĽ
    0.08
    ucci
    0.08
    ä¾Ĺ
    0.07
    isser
    0.07
    è°ł
    0.07
    ä¸Ĭæ¦ľ
    0.07
    è¾¾æłĩ
    0.07
    Activations Density 0.028%

    No Known Activations