© 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. 38849
    Prev
    Next
    INDEX
    Explanations

    known as / called as

    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
    inite
    -0.09
    èĤĮ
    -0.09
     pageTitle
    -0.08
    ä¸Ģç§į
    -0.08
    æī£
    -0.08
    éĺ¶å±Ĥ
    -0.08
    pollo
    -0.08
    ampler
    -0.08
    ç¡®åĪĩ
    -0.08
    åħ¶
    -0.08
    POSITIVE LOGITS
    åı«åģļ
    0.11
    çĨŁçŁ¥
    0.09
    åı«
    0.09
    æīĢè°ĵ
    0.09
    esk
    0.09
    çļĦåIJĦ项
    0.08
    ãĥ¼ãĥĹ
    0.08
    大家éĥ½åľ¨
    0.08
    åħ¬çĶ¨
    0.08
    åIJĦæł·
    0.08
    Activations Density 0.106%

    No Known Activations