© 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. 64051
    Prev
    Next
    INDEX
    Explanations

    file names or types

    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
    arez
    -0.08
    kait
    -0.07
    é¦ģ
    -0.07
    пка
    -0.07
    fea
    -0.07
    åĨ·çĥŃ
    -0.06
    èĬ³èįī
    -0.06
    rens
    -0.06
    orman
    -0.06
    apter
    -0.06
    POSITIVE LOGITS
    ä»Ĭ度ãģ¯
    0.07
     meanwhile
    0.07
    å®Įæķ´çīĪ
    0.07
    åIJĮæł·
    0.07
    çŃīåħ¶ä»ĸ
    0.07
    åı¦å¤ĸä¸Ģç§į
    0.07
    abwe
    0.07
     meantime
    0.07
     infine
    0.07
    ponsible
    0.07
    Activations Density 0.051%

    No Known Activations