© 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. 40638
    Prev
    Next
    INDEX
    Explanations

    č followed by 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
    enticate
    -0.20
    ÑģÑı
    -0.17
    áĢ¸
    -0.14
    ìį¨
    -0.14
    翼翼
    -0.13
    jenigen
    -0.13
    ãģĺãĤģ
    -0.13
    ions
    -0.12
    Ñĩом
    -0.11
    머ëĭĪ
    -0.11
    POSITIVE LOGITS
    ами
    0.19
    ت
    0.18
    i
    0.16
    zelfde
    0.16
    eu
    0.16
    à¥ĩ
    0.15
    ing
    0.15
    ÙĬ
    0.15
    aus
    0.15
    ity
    0.15
    Activations Density 4.145%

    No Known Activations