© 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. 30439
    Prev
    Next
    INDEX
    Explanations

    stat related terms

    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
    ong
    -0.09
    å·¥ä¸ļ大åѦ
    -0.09
    olds
    -0.09
    iÄĻ
    -0.09
    ãĤ¹ãĤ¯
    -0.09
    _kses
    -0.09
    ance
    -0.09
     Stuart
    -0.08
    Å¡t
    -0.08
    ण
    -0.08
    POSITIVE LOGITS
    emachine
    0.17
    istic
    0.14
    istical
    0.13
    itics
    0.13
    icians
    0.13
    utory
    0.12
    ISTICS
    0.12
    ellite
    0.10
    USES
    0.10
     quo
    0.10
    Activations Density 0.041%

    No Known Activations