© 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. 17715
    Prev
    Next
    INDEX
    Explanations

    Chris and surname

    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
    AutoSize
    -0.09
    lef
    -0.09
     оÑĤдел
    -0.09
     Hanna
    -0.09
    iniz
    -0.09
    ç³ľ
    -0.09
    çľĭä»ĸ
    -0.08
    orest
    -0.08
    åıĮè¾¹
    -0.08
    é«Ģ
    -0.08
    POSITIVE LOGITS
    饮æĸĻ
    0.09
     backbone
    0.09
    PAD
    0.08
    éĿ´
    0.08
    åģ¥åħ¨
    0.08
    illo
    0.08
    آخر
    0.07
    hait
    0.07
    éĹ³
    0.07
    åIJĮä¸Ģ
    0.07
    Activations Density 0.047%

    No Known Activations