© 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. 47003
    Prev
    Next
    INDEX
    Explanations

    charged or public

    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
     rather
    -0.08
    ãģ§ãģ¯ãģªãģı
    -0.08
    ä¸įèµ°
    -0.08
    scriptions
    -0.08
    almaz
    -0.08
     Rather
    -0.08
    èĢĮä¸įæĺ¯
    -0.08
    èĢĮéĿŀ
    -0.08
     ìķĦëĭĪëĿ¼
    -0.08
    itera
    -0.08
    POSITIVE LOGITS
    esame
    0.06
     ones
    0.06
    æīĵ
    0.06
    ãĥĪãĥŃ
    0.06
    ä¸Ģå¾ĭ
    0.06
     lohnt
    0.06
    èĽ¾
    0.06
    åĨĴ
    0.06
    ä½IJ
    0.06
    å½ĵæľĪ
    0.06
    Activations Density 0.197%

    No Known Activations