© 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. 48072
    Prev
    Next
    INDEX
    Explanations

    and Gamma

    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
    zb
    -0.07
    oly
    -0.07
    è·¯éĢı
    -0.07
    hoc
    -0.07
    ajar
    -0.07
    ะ
    -0.07
    ä»¥ä¹łè¿ijå¹³
    -0.07
    ä¸Ģè¦ģ
    -0.06
    +(\
    -0.06
    iets
    -0.06
    POSITIVE LOGITS
    çIJĨçĶ±æĺ¯
    0.08
    ariato
    0.07
    idian
    0.07
    åıĪå¦Ĥ
    0.07
    åѦä¸İ
    0.07
    缮æłĩæĺ¯
    0.07
    åŃ©åŃIJæĺ¯
    0.07
    代人
    0.06
    ym
    0.06
    å°´
    0.06
    Activations Density 0.072%

    No Known Activations