© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22872
    Prev
    Next
    INDEX
    Explanations

    expectation of value

    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
    夸
    -0.07
    ément
    -0.07
    éĿĴæĿ¾
    -0.07
    док
    -0.07
    仪
    -0.06
    éĩijåĪļ
    -0.06
    ä¹ī
    -0.06
    arella
    -0.06
    éķ¿çŁŃ
    -0.06
    iliation
    -0.06
    POSITIVE LOGITS
    SSF
    0.07
    ottie
    0.07
    rone
    0.07
    otan
    0.07
    è°ĪåıĬ
    0.07
    æ±ĩ款
    0.07
    rug
    0.06
    tauf
    0.06
     sided
    0.06
    rail
    0.06
    Activations Density 0.001%

    No Known Activations