© 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. 32225
    Prev
    Next
    INDEX
    Explanations

    inclined, angled, slanted

    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
    绽
    -0.10
    воÑĢ
    -0.08
    naire
    -0.08
    ÑĢай
    -0.08
    客æ°Ķ
    -0.08
     Gap
    -0.08
     material
    -0.08
    ulatory
    -0.07
    Gap
    -0.07
    æ°Ķæ°Ľ
    -0.07
    POSITIVE LOGITS
    ç¬ŀ
    0.09
    ESH
    0.09
    æ½ŀ
    0.09
     Rom
    0.09
    éĺ¿æ£®
    0.09
    .overflow
    0.09
     Emm
    0.09
    emm
    0.09
    人æĢ§åĮĸ
    0.09
    аÑĢам
    0.09
    Activations Density 0.061%

    No Known Activations