© 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. 21745
    Prev
    Next
    INDEX
    Explanations

    titles, names, and suffixes

    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
    éĢIJ
    -0.09
    æ¿¡
    -0.08
    åħ³åı£
    -0.08
    нÑĮ
    -0.08
    æĿĤå¿Ĺ
    -0.08
    yna
    -0.08
    _UNS
    -0.08
    è¿ĻæĿ¡
    -0.08
    aser
    -0.08
    wards
    -0.08
    POSITIVE LOGITS
    家æĹı
    0.10
     himself
    0.09
    åħĦ
    0.09
    LastName
    0.09
    esy
    0.09
     Family
    0.09
     Brothers
    0.09
    åı£å¾Ħ
    0.09
    åı£ä¸Ń
    0.09
    èį¦
    0.08
    Activations Density 0.290%

    No Known Activations