© 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. 9049
    Prev
    Next
    INDEX
    Explanations

    ID followed by closing parenthesis

    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
    ney
    -0.09
    å±ĬæŶ
    -0.09
    æĸ¯é¡¿
    -0.08
    SHOT
    -0.08
    olut
    -0.08
    .sap
    -0.08
    ÙİØ°
    -0.08
    ensburg
    -0.08
    oret
    -0.08
    ä½ĵéŃĦ
    -0.08
    POSITIVE LOGITS
    èĦ±
    0.08
    ä¼´
    0.07
    ↵↵
    0.06
    çŃīçŃī
    0.06
    ↵
    0.06
    ugi
    0.06
    å¤ĸ
    0.06
    åģĩ
    0.06
    å¤ļ
    0.06
    æľĢéĩįè¦ģçļĦæĺ¯
    0.05
    Activations Density 0.163%

    No Known Activations