© 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. 50428
    Prev
    Next
    INDEX
    Explanations

    think about

    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
    åĢĺ
    -0.11
    itta
    -0.10
    uden
    -0.10
    IMER
    -0.09
    åĩłå¹´
    -0.09
    æĻ¯è§Ĥ
    -0.09
    æĢ»è£ģ
    -0.09
    WARDS
    -0.09
    perimental
    -0.09
    çĽ¸å¯¹æĿ¥è¯´
    -0.09
    POSITIVE LOGITS
    让å®ĥ
    0.09
    ç¼£
    0.08
    ingly
    0.08
     Gould
    0.08
    åĨħåľ°
    0.08
    Angel
    0.07
    éķ³
    0.07
    è¿Ļ个æŶåĢĻ
    0.07
     jer
    0.07
     Golden
    0.07
    Activations Density 0.008%

    No Known Activations