© 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. 17485
    Prev
    Next
    INDEX
    Explanations

    http(s):// or #ifndef

    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
    ftware
    -0.08
    èī¯åĵģ
    -0.07
    èĢĮä¸Ķæĺ¯
    -0.07
    anguages
    -0.07
    kea
    -0.07
    aro
    -0.07
    ockey
    -0.07
    asuk
    -0.07
    çī¹éĽĨ
    -0.07
    å¤ļ好
    -0.07
    POSITIVE LOGITS
    Ñĸй
    0.07
    parate
    0.07
    sth
    0.06
    ½ij
    0.06
    _any
    0.06
    ersed
    0.06
    çł´
    0.06
    å§ĵ
    0.06
    zer
    0.06
    髦
    0.06
    Activations Density 0.993%

    No Known Activations