© 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. 13796
    Prev
    Next
    INDEX
    Explanations

    rounding numbers to decimal places

    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
    lå
    -0.08
    ä¹±
    -0.08
    ืà¸Ķ
    -0.08
    ä¸Ģå¤ķ
    -0.08
    ÙĨاÙħ
    -0.08
    ocie
    -0.08
    .Setup
    -0.07
    æ¹¾åĮº
    -0.07
    大å¹ħä¸ĭéĻį
    -0.07
     componentDid
    -0.07
    POSITIVE LOGITS
    9
    0.06
    Digits
    0.06
    té
    0.06
    åĪ°èĢģ
    0.06
     digit
    0.06
     digits
    0.06
    éģĵ
    0.06
    tor
    0.06
    Digit
    0.06
    éĽį
    0.06
    Activations Density 0.001%

    No Known Activations