© 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. 11021
    Prev
    Next
    INDEX
    Explanations

    providing process outcomes

    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
    ç¼Ľ
    -0.10
    ynos
    -0.10
    æij¸
    -0.10
    游æĪıçݩ家
    -0.10
    ooks
    -0.09
    åĴİ
    -0.09
    çĶ¨æīĭ
    -0.09
    alte
    -0.09
    è¢Ĥ
    -0.09
    æĪijåİ»
    -0.09
    POSITIVE LOGITS
     purposes
    0.13
     sake
    0.12
    ró
    0.09
    oso
    0.09
    è´»
    0.09
    è¿ĺ
    0.08
    ç«ŀäºīä¼ĺåĬ¿
    0.08
    è¿ĺå¾Ĺ
    0.08
    éĴ¥
    0.08
    羧
    0.08
    Activations Density 0.342%

    No Known Activations