© 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. 49041
    Prev
    Next
    INDEX
    Explanations

    command line options

    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
    å²Ĺ
    -0.10
    CallableWrapper
    -0.10
     Diy
    -0.10
    宫
    -0.10
    ëĭ´
    -0.09
     sourceMapping
    -0.09
    åİŁæĿ¥çļĦ
    -0.09
    èĩªçIJĨ
    -0.09
     intercept
    -0.09
    ADS
    -0.09
    POSITIVE LOGITS
     option
    0.11
     Option
    0.10
     options
    0.10
    éĢī项
    0.09
    åĤį
    0.09
    option
    0.09
    æĺĨ
    0.09
     (--
    0.09
    Option
    0.08
    getOption
    0.08
    Activations Density 0.237%

    No Known Activations