© 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. 52828
    Prev
    Next
    INDEX
    Explanations

    common suffixes or name parts

    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
    ness
    -0.23
    nya
    -0.21
    lah
    -0.19
    ãģĹãģ¾ãģĨ
    -0.19
    ãģĦãģ¾ãģĻ
    -0.17
    ãģĵãģ¨ãģ¯
    -0.15
    sWith
    -0.15
    sw
    -0.15
    ss
    -0.15
    ãģĵãģ¨
    -0.15
    POSITIVE LOGITS
    Ùĭ
    0.23
    ughter
    0.17
    ught
    0.17
    ughty
    0.15
    frica
    0.15
    oui
    0.14
    eus
    0.13
    uteur
    0.13
    ughters
    0.13
    egis
    0.13
    Activations Density 1.309%

    No Known Activations