© 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. 17748
    Prev
    Next
    INDEX
    Explanations

    choice or 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
    æģ¯
    -0.10
    ç¢İ
    -0.09
    声
    -0.08
    寻
    -0.08
     sound
    -0.08
    æĸ¥
    -0.08
    éħŀ
    -0.08
    же
    -0.08
    dro
    -0.08
     dro
    -0.08
    POSITIVE LOGITS
     choice
    0.22
    çļĦéĢīæĭ©
    0.22
     choices
    0.21
    choice
    0.20
    éĢīæĭ©
    0.20
    Choice
    0.19
    choices
    0.19
     Choice
    0.19
    .choice
    0.18
     Choices
    0.18
    Activations Density 0.098%

    No Known Activations