© 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. 54350
    Prev
    Next
    INDEX
    Explanations

    business weekday or working hours

    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
    GLOBALS
    -0.09
    беж
    -0.09
    æĪIJåĬŁçļĦ
    -0.09
    æķ£æŃ¥
    -0.09
    æıĨ
    -0.09
    .EqualTo
    -0.09
    使çĶ¨èĢħæĪĸ
    -0.09
    iá»ĥu
    -0.09
    è´¨æĦŁ
    -0.09
    íĿ¥
    -0.09
    POSITIVE LOGITS
    mail
    0.09
     Anchor
    0.08
    ong
    0.08
    éĶļ
    0.08
     anchor
    0.08
    ih
    0.08
    mmo
    0.08
    anna
    0.08
    çĦĻ
    0.08
    æī§æķĻ
    0.08
    Activations Density 0.010%

    No Known Activations