© 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. 63024
    Prev
    Next
    INDEX
    Explanations

    stem group, extinct genus, primitive appearance

    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
    æįį
    -0.09
    åŃĶéĽĢ
    -0.09
    åĩ¤åĩ°
    -0.08
    帳
    -0.08
    -caret
    -0.08
    Snake
    -0.08
    uku
    -0.08
    åĨĴ
    -0.08
    å¸IJ
    -0.08
    åħ»æĬ¤
    -0.08
    POSITIVE LOGITS
    å±İ
    0.11
    æݸ
    0.11
    åħ¨èº«
    0.10
    TEM
    0.10
    åłij
    0.09
    ivo
    0.09
    æľªæĪIJå¹´
    0.09
    lean
    0.09
    .nil
    0.09
    å¿ĥæĢģ
    0.09
    Activations Density 0.187%

    No Known Activations