© 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. 32910
    Prev
    Next
    INDEX
    Explanations

    use case: automation

    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
    artal
    -0.08
    ä½ľåĪĻ
    -0.08
    å±
    -0.08
    éŨéĶģ
    -0.07
    ulas
    -0.07
    éĶ¦æłĩ
    -0.07
    <|box_end|>
    -0.07
    çľī
    -0.07
    å½Ĵå±ŀ
    -0.07
    \"
    -0.07
    POSITIVE LOGITS
    çħĮ
    0.07
    ICT
    0.07
    .hex
    0.06
    _failed
    0.06
    ä¸Ńå¤ĸ
    0.06
    éħįä¿¡
    0.06
    è°¨
    0.06
    INF
    0.06
     aanb
    0.06
     darn
    0.06
    Activations Density 0.953%

    No Known Activations