© 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. 57694
    Prev
    Next
    INDEX
    Explanations

    Search; This Blog

    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
     Portug
    -0.10
    åľ¨ä¸ŃåĽ½
    -0.10
    çĦ¶æĺ¯
    -0.09
    çįIJ
    -0.09
     Eid
    -0.09
     Ñģог
    -0.08
    å¯Ł
    -0.08
    unda
    -0.08
    çİĩåħĪ
    -0.08
    /if
    -0.08
    POSITIVE LOGITS
    able
    0.10
    ðŁĶį
    0.10
    æIJľç´¢
    0.09
    .Search
    0.09
    ä¿Ŀç¨İ
    0.09
    /Search
    0.09
    uffix
    0.08
     AREA
    0.08
    ableObject
    0.08
    çijĢ
    0.08
    Activations Density 0.029%

    No Known Activations