© 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. 62200
    Prev
    Next
    INDEX
    Explanations

    cabinet positions

    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
    稿
    -0.09
    沤
    -0.09
    ignment
    -0.09
    æ¤ħ
    -0.09
    åħļé£İ
    -0.09
    åĨįä¹Łä¸į
    -0.09
    ì¹Ń
    -0.08
    oner
    -0.08
    -0.08
    iction
    -0.08
    POSITIVE LOGITS
     thá»Ŀ
    0.11
    鬯
    0.10
    rement
    0.10
    eer
    0.09
    ry
    0.08
    ele
    0.08
    éŨåīį
    0.08
     Traverse
    0.08
     Doors
    0.08
    ç¡IJ
    0.08
    Activations Density 0.004%

    No Known Activations