© 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. 28410
    Prev
    Next
    INDEX
    Explanations

    help or code

    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
    urant
    -0.08
    çķĮ
    -0.08
    gan
    -0.07
    åĩ½
    -0.07
    çīĪæĿĥä¸İåħį责声æĺİ
    -0.07
    empa
    -0.07
    éĺij
    -0.07
    èĢĮå·²
    -0.07
     па
    -0.07
    çŃīåįķä½į
    -0.07
    POSITIVE LOGITS
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.07
    cul
    0.07
    ỹ
    0.07
    osu
    0.07
    azel
    0.07
     steps
    0.07
    好æĥ³
    0.07
    æŃ¥éª¤
    0.07
    atine
    0.07
    å°ĨçIJĥ
    0.07
    Activations Density 0.003%

    No Known Activations