© 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. 19845
    Prev
    Next
    INDEX
    Explanations

    phrasing of state or status

    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
    agus
    -0.09
    æĸ°åĬłåĿ¡
    -0.08
    åı¯æĥ³
    -0.08
    avel
    -0.08
    _CODEC
    -0.08
    ữa
    -0.08
    asilan
    -0.08
    langen
    -0.08
    æĪĸå°ij
    -0.08
     ÐĶело
    -0.08
    POSITIVE LOGITS
    å²ģçļĦæŶåĢĻ
    0.07
    <u
    0.07
    ________
    0.07
     ____
    0.06
    ibel
    0.06
     ________
    0.06
     ______
    0.06
    éĩįè¦ģçļĦä½ľçĶ¨
    0.06
    è¿Ļæł·ä¸Ģç§į
    0.06
    ____
    0.06
    Activations Density 0.749%

    No Known Activations