© 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. 64873
    Prev
    Next
    INDEX
    Explanations

    IB, A, B, stage, state

    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
    enf
    -0.07
    rej
    -0.07
    queira
    -0.07
    æħij
    -0.06
    ery
    -0.06
    åIJİè¿Ľ
    -0.06
    åľ¨ä¹İ
    -0.06
    agaan
    -0.06
    reira
    -0.06
    èĢ»
    -0.06
    POSITIVE LOGITS
    zzo
    0.08
    chter
    0.08
    idor
    0.07
    вÑĢо
    0.07
    -meta
    0.07
    _#{
    0.07
    äºĮåŃĹ
    0.07
     Awake
    0.07
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    0.07
    oidal
    0.07
    Activations Density 0.010%

    No Known Activations