© 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. 9772
    Prev
    Next
    INDEX
    Explanations

    printed circuit boards

    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
    qus
    -0.09
    otte
    -0.09
    _WIN
    -0.08
    erot
    -0.08
    çĶŁäº§èĥ½åĬĽ
    -0.08
    èµ
    -0.08
    zel
    -0.08
    ä»İä¸ļ人åijĺ
    -0.08
    _ENTRIES
    -0.08
    _glob
    -0.08
    POSITIVE LOGITS
    å¹³åı°ä¸Ĭ
    0.13
    ä¸ĬçļĦ
    0.13
    å¹³åı°
    0.11
    ãĥľãĥ¼ãĥī
    0.11
    ä¸Ĭæľī
    0.11
    -platform
    0.10
     platforms
    0.10
    èĥĮéĿ¢
    0.10
    board
    0.10
    æĿ¿
    0.10
    Activations Density 0.207%

    No Known Activations