© 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. 57894
    Prev
    Next
    INDEX
    Explanations

    blog, review, source, cart, collection, company, definition, daily

    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
    对èĩªå·±çļĦ
    -0.11
    çŁ¥éģĵèĩªå·±
    -0.10
    å±ŀäºİèĩªå·±
    -0.10
    actics
    -0.09
    交éĢļ
    -0.09
    esor
    -0.09
     конкÑĥÑĢÑģ
    -0.09
    å¯Įæľī
    -0.09
    æĪIJ为ä¸Ģ个
    -0.08
    ä¸ĩ家
    -0.08
    POSITIVE LOGITS
    她们
    0.09
     Maher
    0.08
    éĩįå¿ĥ
    0.08
     jack
    0.08
    ad
    0.08
    èĮľ
    0.08
     possible
    0.07
    åħ±åĪĽ
    0.07
    immer
    0.07
     must
    0.07
    Activations Density 0.093%

    No Known Activations