© 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. 1464
    Prev
    Next
    INDEX
    Explanations

    Syracuse University, Sierra Leone, Sicily places

    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
    jee
    -0.09
    stell
    -0.08
    ız
    -0.08
    chein
    -0.08
    ishing
    -0.08
    å¾Ĺ罪
    -0.08
    çĤ®
    -0.08
    ings
    -0.08
     Chatt
    -0.08
    份é¢Ŀ
    -0.08
    POSITIVE LOGITS
    ronics
    0.10
    otime
    0.10
    rd
    0.09
    ç¾İ人
    0.09
    ric
    0.09
     Conc
    0.09
    conc
    0.09
    åĩ¹
    0.09
    prove
    0.09
    ä¸Ģåı£
    0.09
    Activations Density 0.005%

    No Known Activations