© 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. 56129
    Prev
    Next
    INDEX
    Explanations

    section on

    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
    tur
    -0.08
    ICS
    -0.08
    ä¸Ģ举
    -0.08
    fol
    -0.08
    elin
    -0.08
    _FN
    -0.08
    åºĦåĽŃ
    -0.08
     Fol
    -0.08
    .credentials
    -0.08
    éħ¢
    -0.08
    POSITIVE LOGITS
    [section
    0.14
     sections
    0.13
     section
    0.13
    (section
    0.12
    .Section
    0.12
    段
    0.12
    .sections
    0.12
    section
    0.12
    SECTION
    0.12
    ä¸Ģ段
    0.12
    Activations Density 0.131%

    No Known Activations