© 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. 27506
    Prev
    Next
    INDEX
    Explanations

    seeking information or a solution

    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
    許å¤ļ
    -0.10
    ụ
    -0.09
    atif
    -0.09
     Hữu
    -0.09
     многиÑħ
    -0.08
    indr
    -0.08
    apon
    -0.08
    许å¤ļ
    -0.08
    å¾Ī好çļĦ
    -0.08
    izards
    -0.08
    POSITIVE LOGITS
    çģµæĦŁ
    0.12
    çªģçł´åı£
    0.11
    OrCreate
    0.11
    踪
    0.10
    åħ±é¸£
    0.10
    èĽĽ
    0.10
    çļĦè¿ĩç¨ĭä¸Ń
    0.09
    æģ©
    0.09
    足迹
    0.09
    åĩºè·¯
    0.09
    Activations Density 0.134%

    No Known Activations