© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41035
    Prev
    Next
    INDEX
    Explanations

    "how much", "time is", "were you", "owns the", "are your"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ~~
    -0.07
    å°¤åħ¶
    -0.07
    espo
    -0.07
    诸å¦Ĥ
    -0.07
    å°¤åħ¶æĺ¯
    -0.06
    åĨ³ç®Ĺ
    -0.06
    åĽłä¸ºä½ł
    -0.06
    鼷åIJĮ
    -0.06
    å¦Ĥä½ķåİ»
    -0.06
    çļĦåĩºçİ°
    -0.06
    POSITIVE LOGITS
    æĺ¯å¤ļå°ij
    0.09
    indle
    0.07
    )?
    0.07
    åªĽåªĽ
    0.07
    æį®äºĨ解
    0.07
    кÑĢ
    0.07
    äºĨå¤ļå°ij
    0.07
     berapa
    0.07
    ifar
    0.07
     notable
    0.07
    Activations Density 0.018%

    No Known Activations