© 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. 22819
    Prev
    Next
    INDEX
    Explanations

    mentor and mentorship

    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
    à¸ķรà¸ĩ
    -0.10
    (strip
    -0.09
    adia
    -0.09
    addle
    -0.09
    .Toolkit
    -0.08
    常å§Ķä¼ļ
    -0.08
     anunci
    -0.08
    à¸Ŀาà¸ģ
    -0.08
     дол
    -0.08
    -bordered
    -0.08
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.14
    æľŁåĨħ
    0.11
    ship
    0.11
    acular
    0.10
    chaft
    0.10
    æĸ°åħ´äº§ä¸ļ
    0.10
    ched
    0.09
    åIJĪä½ľåħ³ç³»
    0.09
    輩
    0.09
    ering
    0.09
    Activations Density 0.011%

    No Known Activations