© 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. 3183
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and code

    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
    éĿŀ常快
    -0.07
    éĹ»åĪ°
    -0.07
    çĻ½æĿ¡
    -0.06
     felon
    -0.06
     Threshold
    -0.06
    oun
    -0.06
    \f
    -0.06
    +S
    -0.06
    (optional
    -0.06
    _threshold
    -0.06
    POSITIVE LOGITS
    æ»¡çľ¼
    0.08
    usi
    0.08
    çĺ
    0.08
    osat
    0.08
    æĤ¬
    0.08
    pector
    0.07
    edy
    0.07
    _Em
    0.07
    )&&(
    0.07
    걸
    0.07
    Activations Density 0.004%

    No Known Activations