© 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. 3091
    Prev
    Next
    INDEX
    Explanations

    procedure

    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
    itudes
    -0.09
    ower
    -0.09
    occa
    -0.09
    IMUM
    -0.09
    quist
    -0.09
     behalf
    -0.09
    uration
    -0.09
     nhau
    -0.08
    /close
    -0.08
    owed
    -0.08
    POSITIVE LOGITS
    EDURE
    0.11
    sweise
    0.10
    er
    0.08
    ly
    0.08
    aan
    0.08
    ĺ
    0.08
    aux
    0.08
    ä¸įå¦Ļ
    0.07
    hled
    0.07
     TForm
    0.07
    Activations Density 0.039%

    No Known Activations