© 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. 62295
    Prev
    Next
    INDEX
    Explanations

    COUNTY

    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
    ritz
    -0.07
    .displayName
    -0.07
    èŃ¯
    -0.07
    åIJĮæĹ¶ä¹Łåı¯ä»¥
    -0.06
    ä¹ĭæŃĮ
    -0.06
    å®ļåĪ¶
    -0.06
    lus
    -0.06
    ترات
    -0.06
    >:
    -0.06
    usty
    -0.06
    POSITIVE LOGITS
    移åĪ°
    0.08
    ì¶ķ
    0.07
    ibun
    0.07
    schutz
    0.07
    paren
    0.07
    emen
    0.07
    çµŀãĤĬ
    0.07
     Wrong
    0.07
    less
    0.07
    ä¸ĢæĪIJ
    0.07
    Activations Density 0.001%

    No Known Activations