© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4162
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    å¼ģ
    -0.07
    вок
    -0.07
    omÄĽ
    -0.07
     ::=
    -0.06
    uzzi
    -0.06
    .series
    -0.06
    edr
    -0.06
    ứa
    -0.06
    åĪĨä¹ĭ
    -0.06
    ķ
    -0.06
    POSITIVE LOGITS
    upt
    0.07
    nud
    0.07
    _INLINE
    0.07
    æ
    0.06
    ething
    0.06
    ervice
    0.06
    èĢ½
    0.06
    ondre
    0.06
    xAB
    0.06
    uns
    0.06
    Activations Density 0.001%

    No Known Activations