© 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. 58095
    Prev
    Next
    INDEX
    Explanations

    advertisement headlines

    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
    好åIJĹ
    -0.10
    antz
    -0.09
    _scal
    -0.08
    iveness
    -0.08
    ulator
    -0.08
    çIJĨ
    -0.08
     Thi
    -0.08
    вели
    -0.08
    .segment
    -0.08
    åĬ©åѦ
    -0.08
    POSITIVE LOGITS
    èĭĩ
    0.12
    æ°´æµģ
    0.09
    ï¼ģ
    0.09
    é¹³
    0.09
    æīįæľī
    0.09
    请çĤ¹åĩ»
    0.09
    èĤĦ
    0.09
    ANN
    0.09
    éĩį度
    0.08
    .sqlite
    0.08
    Activations Density 0.098%

    No Known Activations