© 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. 28050
    Prev
    Next
    INDEX
    Explanations

    mon, sunday, monday

    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
    åĬ¡
    -0.08
    çĪĨ
    -0.08
    è½»è½»åľ°
    -0.08
    orem
    -0.08
    _CPP
    -0.07
     happ
    -0.07
     Ø£ÙĬض
    -0.07
    ä¸ĵçĶ¨
    -0.07
    หาย
    -0.07
    erb
    -0.07
    POSITIVE LOGITS
     ltd
    0.11
     SimpleName
    0.10
    'S
    0.09
     sunday
    0.09
     catholic
    0.09
     monday
    0.09
     america
    0.09
    bidden
    0.09
    WISE
    0.08
    DataGridViewTextBoxColumn
    0.08
    Activations Density 0.918%

    No Known Activations