© 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. 32583
    Prev
    Next
    INDEX
    Explanations

    favorite X

    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
    åıªè¦ģæľī
    -0.11
    ä¸Ģå¼ł
    -0.10
     COPYRIGHT
    -0.09
     одна
    -0.09
    åĽłä¸ºåľ¨
    -0.09
    é£İéĩĩ
    -0.09
    orce
    -0.09
    .kr
    -0.08
    åĽłä¸ºå®ĥ
    -0.08
     вÑģÑıк
    -0.08
    POSITIVE LOGITS
    éħĬ
    0.10
    utow
    0.09
    ī
    0.09
    WithContext
    0.09
    byss
    0.09
    éĨħ
    0.09
    /current
    0.09
    å²Ľå±¿
    0.08
    è¯İ
    0.08
    amt
    0.08
    Activations Density 0.008%

    No Known Activations