© 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. 57407
    Prev
    Next
    INDEX
    Explanations

    researchers say or suggested

    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
    楷
    -0.09
    æĪIJçĨŁçļĦ
    -0.08
    èĴĻ
    -0.08
    ì°°
    -0.08
    EntryPoint
    -0.08
    sville
    -0.08
    éĶ¡
    -0.08
    ä¸įä¸ĭ
    -0.08
    çĻ¾ç§ij
    -0.08
    ç¾Ķ
    -0.08
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥
    0.10
    ç»ĵ论
    0.09
    è¿Ļ份
    0.09
    ä¸įåħį
    0.09
    æķ¦
    0.09
     пÑĢоведен
    0.09
    好æ¶Īæģ¯
    0.09
    åIJİç»Ń
    0.09
    çłĶ究æĪIJæŀľ
    0.09
    ä¸ĵ家ç»Ħ
    0.08
    Activations Density 0.092%

    No Known Activations