© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11911
    Prev
    Next
    INDEX
    Explanations

    ends with l

    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
    ìľ¼ë¡ľ
    -0.16
    elor
    -0.12
    ãģ¾ãģĹãģŁ
    -0.12
    ìľ¼ë¡ľëĬĶ
    -0.11
    els
    -0.11
    elsen
    -0.11
    ãĤĭãģ¨
    -0.11
    ep
    -0.11
    es
    -0.10
    ally
    -0.10
    POSITIVE LOGITS
    ambda
    0.15
    ibrary
    0.14
    izabeth
    0.13
    ounge
    0.13
    aunch
    0.13
    ucid
    0.13
    attice
    0.13
    anguage
    0.13
    inux
    0.13
    buquerque
    0.12
    Activations Density 3.212%

    No Known Activations