© 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. 27427
    Prev
    Next
    INDEX
    Explanations

    what about

    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
    leen
    -0.10
    çīĮ
    -0.09
    主è¦ģæľī
    -0.09
    享
    -0.09
    apo
    -0.08
    ứ
    -0.08
    éĥİ
    -0.08
    anyl
    -0.08
    ATS
    -0.08
    Extent
    -0.08
    POSITIVE LOGITS
    éĤ£äºĽ
    0.12
     bul
    0.09
    ãģĦãģij
    0.09
    æį¨
    0.09
    诸å¤ļ
    0.09
    åĩ«
    0.09
    åIJİæľŁ
    0.09
    ippy
    0.09
    .nlm
    0.08
    enville
    0.08
    Activations Density 0.014%

    No Known Activations