© 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. 34395
    Prev
    Next
    INDEX
    Explanations

    measure, assessment, index, tool

    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
    /cpu
    -0.10
    CPU
    -0.10
    éĬ·
    -0.09
    çł´è§£
    -0.09
     CPU
    -0.09
    çł´
    -0.08
    åħīåѦ
    -0.08
     cpu
    -0.08
    illusion
    -0.08
    .Marshal
    -0.08
    POSITIVE LOGITS
    æµĭ
    0.11
     measures
    0.11
    尺度
    0.10
     measure
    0.09
    ä¸Ī
    0.09
    測
    0.09
    ä¸Ģè´¯
    0.09
    涵çĽĸ
    0.09
    measure
    0.09
    .measure
    0.09
    Activations Density 0.258%

    No Known Activations