© 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. 11242
    Prev
    Next
    INDEX
    Explanations

    lists of items, often separated by commas or semicolons

    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
    åĪ°
    -0.07
    大äºĭ
    -0.07
    é«ĺä½İ
    -0.06
    ãĢįï¼Ī
    -0.06
    lott
    -0.06
    olg
    -0.06
    teste
    -0.06
    nl
    -0.06
     sid
    -0.06
    oord
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.15
    注æĦıå®īåħ¨
    0.08
    --)
    0.08
     )**
    0.08
    ä¸ĭ称
    0.08
    inci
    0.08
     ):
    0.08
     );
    0.08
    以ä¸ĭç®Ģ称
    0.08
    è¿ĶåĽŀ缮å½ķ
    0.08
    Activations Density 0.177%

    No Known Activations