© 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. 50080
    Prev
    Next
    INDEX
    Explanations

    redistribution and use permitted

    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
    ness
    -0.14
    ation
    -0.13
    Ø©
    -0.13
    RARY
    -0.12
    ÑİÑĤ
    -0.11
    ималÑĮ
    -0.11
    entication
    -0.10
    ively
    -0.10
    idity
    -0.10
    àµį
    -0.10
    POSITIVE LOGITS
    hips
    0.12
    ä½Ĩä¸įéĻIJäºİ
    0.11
    Ùĩ
    0.11
    er
    0.10
    Ñı
    0.10
     Äijặn
    0.10
    ëį°
    0.10
    hlas
    0.09
    ../../
    0.09
    ffects
    0.09
    Activations Density 0.497%

    No Known Activations