© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38007
    Prev
    Next
    INDEX
    Explanations

    Jake Owen, .net, Willis

    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
    è¢ľ
    -0.08
    èĦĬ
    -0.08
    妻
    -0.08
    仨
    -0.08
    æ¸ħæ¥ļ
    -0.08
    微信åı·
    -0.08
    uen
    -0.07
    çĻĸ
    -0.07
    秧
    -0.07
    asco
    -0.07
    POSITIVE LOGITS
    _logged
    0.10
    ervised
    0.10
    หว
    0.10
    erva
    0.09
    æİ¥éĢģ
    0.09
    OrElse
    0.09
    åĢĮ
    0.09
    ervas
    0.09
    è¿İæİ¥
    0.09
    arness
    0.09
    Activations Density 0.009%

    No Known Activations