© 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. 14292
    Prev
    Next
    INDEX
    Explanations

    greater/smaller than

    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
    ä¸įæ¼ı
    -0.07
    ç¬ij
    -0.07
    rove
    -0.06
    ç¿ģ
    -0.06
    ged
    -0.06
    è¤
    -0.06
    ạc
    -0.06
     Bud
    -0.06
    inkan
    -0.06
    atro
    -0.06
    POSITIVE LOGITS
    -than
    0.24
     than
    0.24
    than
    0.23
    _than
    0.21
    Than
    0.18
     Than
    0.18
     THAN
    0.18
     niż
    0.17
    _THAN
    0.16
     kuin
    0.14
    Activations Density 0.437%

    No Known Activations