© 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. 33658
    Prev
    Next
    INDEX
    Explanations

    look on, in, around, inside

    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
    .bat
    -0.10
    èĩªåıij
    -0.09
    ç©°
    -0.08
     excell
    -0.08
    (utils
    -0.08
    bat
    -0.08
    ä¸įæĺİ
    -0.08
    .PO
    -0.08
    çªģåıijäºĭ件
    -0.08
    éĶī
    -0.08
    POSITIVE LOGITS
    ä¸Ģçľ¼
    0.14
    ä¸Ģçľĭ
    0.13
    æľī没æľī
    0.11
    ðŁijĢ
    0.11
    æĺ¯åIJ¦æľī
    0.11
    è±¹
    0.11
     uważ
    0.10
    OrCreate
    0.10
    UGE
    0.10
    æĶ¾çľ¼
    0.09
    Activations Density 0.069%

    No Known Activations