© 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. 10507
    Prev
    Next
    INDEX
    Explanations

    bitcoin, ethereum

    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
    ocha
    -0.07
    ecer
    -0.07
    otre
    -0.07
     vol
    -0.06
     vi
    -0.06
     [].
    -0.06
    ä¸įçł´
    -0.06
     Adler
    -0.06
    é¸
    -0.06
    vi
    -0.06
    POSITIVE LOGITS
    ãģ£ãģŁãĤĬ
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    以åıĬåIJĦç§į
    0.08
    ãģ¿ãĤĦ
    0.08
    以åıĬ
    0.08
    人ãĤĦ
    0.08
    )ãĢģ
    0.07
    以åıĬåľ¨
    0.07
    éĺŁåĴĮ
    0.07
    ì§ĢìĻĢ
    0.07
    Activations Density 0.069%

    No Known Activations