© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9167
    Prev
    Next
    INDEX
    Explanations

    render something

    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
    èµ·æĿ¥äºĨ
    -0.09
    æģ¯
    -0.09
    ÙĨÙħ
    -0.09
    _pres
    -0.09
    راÙģ
    -0.09
    åĢ©
    -0.09
     Chavez
    -0.08
    isma
    -0.08
     Burnett
    -0.08
    _consts
    -0.08
    POSITIVE LOGITS
    edImage
    0.10
    edException
    0.10
    æ²¥
    0.09
    èĭ±éĽĦ
    0.09
    ERO
    0.09
    ãģ²ãģ¨
    0.08
    sink
    0.08
    .githubusercontent
    0.08
    ents
    0.08
    æŨ
    0.08
    Activations Density 0.012%

    No Known Activations