© 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. 17382
    Prev
    Next
    INDEX
    Explanations

    St. John's, Thomas', Francis' names

    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
    åłĤ
    -0.11
     asbestos
    -0.09
    orough
    -0.09
    éĻ¢åī¯éĻ¢éķ¿
    -0.09
    åı±
    -0.09
    Std
    -0.09
    еÑĩно
    -0.09
    hsi
    -0.09
    intl
    -0.08
    wit
    -0.08
    POSITIVE LOGITS
    饯
    0.10
    ÑĢак
    0.08
    票
    0.08
    äºĮ代
    0.08
    erne
    0.08
    æ·¡
    0.08
    åij·
    0.07
    atra
    0.07
     Alexis
    0.07
    uder
    0.07
    Activations Density 0.006%

    No Known Activations