© 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. 52388
    Prev
    Next
    INDEX
    Explanations

    metrics and indicators

    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
    _TC
    -0.10
    éĻĤ
    -0.09
    æij¸ç´¢
    -0.09
    _marshall
    -0.09
    .encoding
    -0.09
    Coder
    -0.09
    (encoding
    -0.09
    alık
    -0.09
    æ¸ł
    -0.09
    _EDITOR
    -0.09
    POSITIVE LOGITS
    æĮĩæłĩ
    0.20
     metrics
    0.17
     Metrics
    0.16
    èĢĥæł¸
    0.14
    metrics
    0.14
    è¡¡éĩı
    0.13
    Metrics
    0.13
    .metrics
    0.12
     measure
    0.12
     metric
    0.12
    Activations Density 0.114%

    No Known Activations