© 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. 49268
    Prev
    Next
    INDEX
    Explanations

    two judges or two rims

    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
    annis
    -0.08
    ä»İæĹł
    -0.08
    ãģłãģijãģ«
    -0.07
    adari
    -0.07
    osci
    -0.07
    ä¸İ人
    -0.07
    RP
    -0.06
    ucks
    -0.06
    ucken
    -0.06
    iker
    -0.06
    POSITIVE LOGITS
    两类
    0.08
     mostly
    0.08
    stype
    0.08
    Ùģت
    0.08
    éĻ¤
    0.08
     unequal
    0.08
     except
    0.07
    åĨįä¸ī
    0.07
     ÙħتÙģاÙĪت
    0.07
    大å¤ļæĺ¯
    0.07
    Activations Density 0.148%

    No Known Activations