© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10531
    Prev
    Next
    INDEX
    Explanations

    YUV or YOLO variations

    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
    åķª
    -0.09
    æĶ¶è´¹æłĩåĩĨ
    -0.09
    æĸ°å½¢åĬ¿
    -0.09
    æĶ¶åĽŀ
    -0.09
    æ°Ľ
    -0.08
    atten
    -0.08
    licas
    -0.08
    æ¢Ĩ
    -0.08
    å°ıçĻ½
    -0.08
    umps
    -0.08
    POSITIVE LOGITS
    ields
    0.14
    psilon
    0.11
    _STRUCT
    0.11
    osemite
    0.11
    缣
    0.10
    uxtap
    0.10
    onas
    0.10
    IELDS
    0.10
    ntax
    0.10
    è¡Į使
    0.10
    Activations Density 0.106%

    No Known Activations