© 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. 22222
    Prev
    Next
    INDEX
    Explanations

    #if directives

    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
    _OCCURRED
    -0.10
    ç½ĹéĤ£
    -0.10
     Blasio
    -0.09
    ÏĦαι
    -0.09
    ê¼
    -0.09
    å§ĶåĨħ
    -0.09
    plode
    -0.09
    hoven
    -0.09
    erii
    -0.08
    nö
    -0.08
    POSITIVE LOGITS
     C
    0.07
    ↵
    0.06
    0.06
     V
    0.06
     L
    0.06
    revision
    0.06
     D
    0.06
    _TRACK
    0.06
     M
    0.06
     P
    0.06
    Activations Density 0.190%

    No Known Activations