© 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. 38075
    Prev
    Next
    INDEX
    Explanations

    phone and device connectivity

    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
    iris
    -0.10
    adas
    -0.09
    .entry
    -0.08
    uro
    -0.08
    trieve
    -0.08
    ç«ŀäºī对æīĭ
    -0.08
    ImageData
    -0.08
    vens
    -0.08
     Komm
    -0.08
    ultiply
    -0.08
    POSITIVE LOGITS
    å¾Īæĸ¹ä¾¿
    0.10
    便åı¯
    0.10
    ç½®äºİ
    0.09
    åĴ«
    0.09
    便ä¼ļ
    0.09
    èĩªå¸¦
    0.09
    çĶ¨æĿ¥
    0.09
    ä¸ļä½Ļ
    0.09
    kept
    0.09
    æľīèī²
    0.09
    Activations Density 0.126%

    No Known Activations