© 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. 47785
    Prev
    Next
    INDEX
    Explanations

    two-byte password

    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
    èĬ¸
    -0.07
    _printer
    -0.07
    cken
    -0.07
    rq
    -0.06
    çĪ±å°Ķ
    -0.06
    raft
    -0.06
     Burlington
    -0.06
     Kash
    -0.06
    åĿª
    -0.06
    uss
    -0.06
    POSITIVE LOGITS
    æµ·çĩķ
    0.07
    erad
    0.07
    aal
    0.07
     Хаб
    0.07
    reich
    0.07
    isal
    0.07
    ToDate
    0.07
    jala
    0.07
    å¥Ĺ
    0.07
    iop
    0.07
    Activations Density 0.037%

    No Known Activations