© 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. 22543
    Prev
    Next
    INDEX
    Explanations

    experiment or experiences

    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
    便ä¼ļ
    -0.10
    amu
    -0.09
    agg
    -0.09
    oric
    -0.08
    aho
    -0.08
    chas
    -0.08
    å¼¯æĽ²
    -0.08
    å¹¿æ³ĽåºĶçĶ¨
    -0.08
    oya
    -0.08
    PIPE
    -0.08
    POSITIVE LOGITS
    å®ŀéªĮ
    0.21
     experiments
    0.20
     experiment
    0.20
    è¯ķéªĮ
    0.19
     Experiment
    0.18
    experiment
    0.17
     ìĭ¤í
    0.17
    Experiment
    0.16
    periments
    0.15
    _experiment
    0.14
    Activations Density 0.149%

    No Known Activations