© 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. 48579
    Prev
    Next
    INDEX
    Explanations

    passionate 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
    ENA
    -0.10
    ustin
    -0.09
    allee
    -0.09
    ÑģÑĤеÑĢ
    -0.09
    /us
    -0.09
    smouth
    -0.08
     ENUM
    -0.08
    spm
    -0.08
    è¿İ
    -0.08
    æĪijå¾Ī
    -0.08
    POSITIVE LOGITS
     about
    0.20
    about
    0.16
    åħ³äºİ
    0.15
     vá»ģ
    0.15
    _about
    0.15
     عÙĨÙĩا
    0.15
     ABOUT
    0.14
     tentang
    0.13
    .about
    0.13
    -about
    0.13
    Activations Density 0.097%

    No Known Activations