© 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. 52269
    Prev
    Next
    INDEX
    Explanations

    journal citations

    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
    ä¸ĢèĤ¡
    -0.09
    åĬ³åĬ¨
    -0.08
    QB
    -0.08
     lip
    -0.08
    stem
    -0.08
     dime
    -0.08
     Cupertino
    -0.08
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    -0.08
    è¿Ļéĥ¨çĶµå½±
    -0.08
    camp
    -0.08
    POSITIVE LOGITS
    .mods
    0.09
    å°ı康
    0.09
    ÑģÑĤе
    0.09
    avan
    0.09
    åĮ¾
    0.09
    /board
    0.08
    lider
    0.08
    Leap
    0.08
    é¢ij
    0.08
    _FWD
    0.08
    Activations Density 0.062%

    No Known Activations