© 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. 15268
    Prev
    Next
    INDEX
    Explanations

    link references like [Table 1]

    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
    ard
    -0.07
    abra
    -0.07
    hut
    -0.06
    æĮij
    -0.06
    ownt
    -0.06
    RL
    -0.06
    ayat
    -0.06
    è©®
    -0.06
    -relative
    -0.06
     strugg
    -0.06
    POSITIVE LOGITS
    éĻªå®¡åijĺ
    0.07
    个æ¡Ī
    0.07
    潦
    0.07
    ÏĢÏĦ
    0.07
     Riot
    0.07
    Ïĥκ
    0.07
    ä¸Ĭ马
    0.07
    ìĸij
    0.07
    ä¸Ĭä¸Ģ页
    0.07
     Ñģимп
    0.07
    Activations Density 0.289%

    No Known Activations