© 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. 15568
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    reen
    -0.06
     verw
    -0.06
    主æ¼Ķ
    -0.06
    AMO
    -0.06
    å®īæİĴ
    -0.06
    æĪij们èĩªå·±
    -0.06
    E
    -0.06
    et
    -0.06
    ored
    -0.06
    èĪª
    -0.06
    POSITIVE LOGITS
    ì¹ĺê°Ģ
    0.08
    _called
    0.08
    ugu
    0.08
    oker
    0.08
    iba
    0.07
    éĻ¤æģ¶
    0.07
    дай
    0.07
    ä»Ģä¹Ī人
    0.07
    ì¹ĺ를
    0.07
    $__
    0.07
    Activations Density 0.000%

    No Known Activations