© 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. 21642
    Prev
    Next
    INDEX
    Explanations

    comic books and automobiles

    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
    AGR
    -0.11
    âľª
    -0.10
    Ãłn
    -0.09
    onym
    -0.09
    opath
    -0.09
    ignal
    -0.08
    èĢģé¼ł
    -0.08
    оÑĦ
    -0.08
    éĢµ
    -0.08
    opes
    -0.08
    POSITIVE LOGITS
    0
    0.09
    ма
    0.09
    2
    0.09
    ãģ¾ãģĦ
    0.09
    3
    0.08
    8
    0.08
    MENT
    0.08
    æķ
    0.08
    9
    0.08
    m
    0.08
    Activations Density 0.014%

    No Known Activations