© 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. 57994
    Prev
    Next
    INDEX
    Explanations

    if no, not, cannot, possible

    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
    é¢Ŀå¤ĸ
    -0.10
    éģIJ
    -0.10
    å¹Ħ
    -0.10
    ISK
    -0.09
    .persistent
    -0.09
    为é¦ĸ
    -0.09
    ÑĦик
    -0.09
    å¤ļäºĨ
    -0.09
    .Accept
    -0.09
    æŃ£çīĪ
    -0.09
    POSITIVE LOGITS
    åıªæľīä¸Ģ个
    0.10
    åŃ£
    0.10
    æĹłåı¯
    0.09
    æľīå¤ļ
    0.09
    there
    0.09
     there
    0.08
    æľī两个
    0.08
    uka
    0.08
    *
    0.08
    çİ°åŃĺ
    0.08
    Activations Density 0.341%

    No Known Activations