© 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. 10659
    Prev
    Next
    INDEX
    Explanations

    comparisons of degree

    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
    morph
    -0.09
    boo
    -0.09
     eb
    -0.09
    ellas
    -0.09
    IMATE
    -0.09
     ÑģебÑı
    -0.09
    trap
    -0.08
    _CY
    -0.08
    Nib
    -0.08
    ä¸Ģè´¯
    -0.08
    POSITIVE LOGITS
     ëįĶìļ±
    0.15
    尤为
    0.14
    æł¼å¤ĸ
    0.14
    æĽ´åĬł
    0.13
    æĦĪåıij
    0.13
    æĦĪåĬł
    0.13
    æĽ´æĺ¯
    0.12
    è¶Ĭåıij
    0.12
    è¿Ľä¸ĢæŃ¥
    0.12
    尤为éĩįè¦ģ
    0.12
    Activations Density 0.058%

    No Known Activations