© 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. 29872
    Prev
    Next
    INDEX
    Explanations

    eagle flying, Horsemen, cover his, SQL script

    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
    åı¨
    -0.10
    家ä¸Ń
    -0.08
    åĩºå¢ĥ
    -0.08
    å¸
    -0.08
    çĭİ
    -0.08
    iou
    -0.08
    åĩºåİĤ
    -0.08
     mole
    -0.08
    åıįæŃ£
    -0.08
    uxt
    -0.08
    POSITIVE LOGITS
    å¦ĤæĦı
    0.10
     lul
    0.09
    cope
    0.09
    apg
    0.09
    .hy
    0.08
    éŁ³åĵį
    0.08
    æĴĴ
    0.08
    èĿ´èĿ¶
    0.08
    asar
    0.08
    平稳
    0.08
    Activations Density 0.068%

    No Known Activations