© 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. 10891
    Prev
    Next
    INDEX
    Explanations

    different with specific examples

    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
    缸å½ĵ
    -0.09
    æŁIJç§į
    -0.09
    ä¸Ģ身
    -0.09
    æŁIJç§įç¨ĭ度
    -0.09
    own
    -0.08
    áºŃn
    -0.08
     reflexivity
    -0.08
    à¹ĥà¸ļ
    -0.08
    ิà¸ķ
    -0.08
    æĽ´å¤ļ精彩
    -0.08
    POSITIVE LOGITS
    iable
    0.25
    iating
    0.23
    iates
    0.20
    ially
    0.19
    iator
    0.18
    iability
    0.17
    ials
    0.17
    iators
    0.16
    iate
    0.14
    -sex
    0.13
    Activations Density 0.096%

    No Known Activations