© 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. 55927
    Prev
    Next
    INDEX
    Explanations

    diazepam and related compounds

    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
    yard
    -0.10
    ÙģØ©
    -0.10
    gers
    -0.10
    ees
    -0.10
    å¡ĺ
    -0.09
    pel
    -0.09
    ìį¨
    -0.09
     thù
    -0.09
    Ùij
    -0.09
    ter
    -0.09
    POSITIVE LOGITS
    ledge
    0.11
    epam
    0.10
    strt
    0.09
    ะ
    0.08
    TagName
    0.08
    icity
    0.08
    涩
    0.08
    ched
    0.08
    upy
    0.08
    æµģè¡ĮçļĦ
    0.08
    Activations Density 0.019%

    No Known Activations