© 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. 1045
    Prev
    Next
    INDEX
    Explanations

    de la

    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
     feas
    -0.09
    é§IJ
    -0.09
    _stand
    -0.09
    æ·ĺ
    -0.08
    _fwd
    -0.08
    _Var
    -0.08
    isks
    -0.08
    ëħ¹
    -0.08
    诵
    -0.08
    饥
    -0.08
    POSITIVE LOGITS
    erial
    0.11
    æľīéĹ®é¢ĺ
    0.09
    æ°´ä¸Ń
    0.09
    æ£ī
    0.08
    onda
    0.08
    çľĭä¸įè§ģ
    0.08
     Dion
    0.08
    人éĢł
    0.08
    lier
    0.08
    chema
    0.08
    Activations Density 0.058%

    No Known Activations