© 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. 10800
    Prev
    Next
    INDEX
    Explanations

    real vector bundle

    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
     Brick
    -0.11
    ãĤ¤ãĥ¤
    -0.11
    趴
    -0.11
     bricks
    -0.10
    寥
    -0.10
    çłĸ
    -0.10
    esser
    -0.10
    å¨ģ
    -0.10
    BOSE
    -0.09
    abox
    -0.09
    POSITIVE LOGITS
    è¢ĭ
    0.10
    产åĵģè´¨éĩı
    0.09
    åºĬä½į
    0.08
    裨
    0.08
     ras
    0.08
    æ³»
    0.08
    åĽĬ
    0.08
    è¢ĭåŃIJ
    0.08
     bags
    0.08
     cort
    0.08
    Activations Density 0.110%

    No Known Activations