© 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. 39136
    Prev
    Next
    INDEX
    Explanations

    android attributes

    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
    å¯Ĩæĸ¯
    -0.08
    客
    -0.08
    hora
    -0.07
    .SuspendLayout
    -0.07
     eventu
    -0.07
    LatLng
    -0.07
    .Ui
    -0.07
    GetY
    -0.07
    æĹ¶èµ·
    -0.07
     Ingy
    -0.07
    POSITIVE LOGITS
    umé
    0.07
    alow
    0.07
    _subtype
    0.06
    mans
    0.06
    igo
    0.06
    ard
    0.06
     trump
    0.06
     Season
    0.06
    çĹĩæĤ£èĢħ
    0.06
    ighth
    0.06
    Activations Density 0.054%

    No Known Activations