© 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. 5570
    Prev
    Next
    INDEX
    Explanations

    making choices

    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
    è¿ĻäºĽä¸ľè¥¿
    -0.10
    仪表
    -0.09
    .pair
    -0.08
    erdale
    -0.08
     Sommer
    -0.08
    æģ°å¥½
    -0.08
    umbo
    -0.08
    EVER
    -0.08
    æł¸å¿ĥæĬĢæľ¯
    -0.08
    çijķ
    -0.08
    POSITIVE LOGITS
     option
    0.22
    éĢī项
    0.20
     alternative
    0.19
     alternatives
    0.18
    option
    0.17
     options
    0.17
    .option
    0.16
     Option
    0.16
     opción
    0.15
    _option
    0.15
    Activations Density 0.127%

    No Known Activations