© 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. 40181
    Prev
    Next
    INDEX
    Explanations

    code file names and email addresses

    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
    "http
    -0.08
    âĢ¦Â»
    -0.07
    _stub
    -0.07
     http
    -0.07
    'http
    -0.07
    dale
    -0.07
    åIJŃ
    -0.06
     [âĢ¦]
    -0.06
    äºĪ
    -0.06
    engo
    -0.06
    POSITIVE LOGITS
     **
    0.09
    elman
    0.08
    ×IJÖ·
    0.07
    -**
    0.07
    æĶ¿éĥ¨
    0.07
    æĸ°åĬłåĿ¡
    0.07
    Unnamed
    0.07
    <|object_ref_start|>
    0.06
    NewLabel
    0.06
    ,proto
    0.06
    Activations Density 0.360%

    No Known Activations