© 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. 61733
    Prev
    Next
    INDEX
    Explanations

    Summary:

    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
    Ĵ·
    -0.08
     č↵ č↵
    -0.08
    USTOM
    -0.08
    AGA
    -0.08
    usch
    -0.08
    usas
    -0.07
    ÑĥÑģÑĤа
    -0.07
    _decorator
    -0.07
    Opacity
    -0.07
    ä»
    -0.07
    POSITIVE LOGITS
    omma
    0.07
    éĢļè¿ĩè¿ĻäºĽ
    0.06
    éĢļè¿ĩ以ä¸Ĭ
    0.06
    These
    0.06
     These
    0.06
     comprises
    0.06
    пÑĤо
    0.06
    èĢĮèĩªå·±
    0.06
    äºĮè¿ŀ
    0.05
    eya
    0.05
    Activations Density 0.001%

    No Known Activations