© 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. 61832
    Prev
    Next
    INDEX
    Explanations

    questions about why or how

    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
    æ´»
    -0.09
     cord
    -0.09
    Extern
    -0.08
    å°Ĭ严
    -0.08
    åºĶ对
    -0.08
    ervo
    -0.08
    ï¸
    -0.07
    è¸Į
    -0.07
     tuned
    -0.07
    çĨŁ
    -0.07
    POSITIVE LOGITS
    论è¯ģ
    0.13
    è¯ģå®ŀ
    0.12
    åĽłæŀľ
    0.12
    说æľį
    0.12
    çłĶ究æĪIJæŀľ
    0.12
    羣çIJĨ
    0.11
    è¿Ļè¯Ŀ
    0.11
    æĩĤå¾Ĺ
    0.11
    éģĵçIJĨ
    0.11
    ç§ijåѦçłĶ究
    0.11
    Activations Density 0.423%

    No Known Activations