© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6818
    Prev
    Next
    INDEX
    Explanations

    sure-fire / sure-win / sure thing / sure to pleased

    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
    æĪijçĽ¸ä¿¡
    -0.10
    ss
    -0.08
    媳
    -0.08
    æĪijå¸ĮæľĽ
    -0.08
    arily
    -0.08
    ers
    -0.08
    æĪijä¸Ģ缴
    -0.08
    nin
    -0.08
    à¹Į
    -0.08
    ces
    -0.08
    POSITIVE LOGITS
     chắn
    0.14
    ties
    0.14
    veillance
    0.13
    heits
    0.12
    emente
    0.12
    tte
    0.12
    comings
    0.11
     rÃłng
    0.11
    èĥĽ
    0.10
    NESS
    0.10
    Activations Density 0.026%

    No Known Activations