© 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. 22409
    Prev
    Next
    INDEX
    Explanations

    cron jobs and scheduling

    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
    icular
    -0.10
    ry
    -0.09
    apy
    -0.09
    éĽĨåĽ¢èĤ¡ä»½
    -0.09
    urar
    -0.09
    овиÑĩ
    -0.08
    åŁ¹è®ŃæľºæŀĦ
    -0.08
    ää
    -0.08
    è¿Ħ
    -0.08
    onn
    -0.08
    POSITIVE LOGITS
    sters
    0.11
    busters
    0.10
    ULER
    0.09
    é¹Ĺ
    0.09
    Ñħо
    0.09
    ple
    0.09
    inals
    0.09
    zilla
    0.09
    itude
    0.09
     tamb
    0.08
    Activations Density 0.022%

    No Known Activations