© 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. 62661
    Prev
    Next
    INDEX
    Explanations

    car body styles

    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
    åĻ¨æĿIJ
    -0.11
    tea
    -0.10
    æīĢåľ¨åľ°
    -0.08
    ively
    -0.08
    åİĨæŶ
    -0.08
    onaut
    -0.08
    .land
    -0.08
    缸è§ģ
    -0.08
     Nagar
    -0.08
    å§IJ
    -0.08
    POSITIVE LOGITS
    æķŀå¼Ģ
    0.10
    ÑĢам
    0.09
    å¼ı
    0.09
    WithTitle
    0.09
    pler
    0.09
    æĪ¢
    0.09
    pling
    0.09
    resse
    0.09
    olib
    0.08
    .biz
    0.08
    Activations Density 0.025%

    No Known Activations