© 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. 40512
    Prev
    Next
    INDEX
    Explanations

    training courses and programs

    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
    å¹´é«ĺèĢĥ
    -0.07
    çĪ¸çĪ¸è¯´
    -0.07
    å°ıåįĩåĪĿ
    -0.07
    udent
    -0.07
    åIJĪä½ľåħ±èµ¢
    -0.06
    ä¸ŃèĢĥ
    -0.06
    alow
    -0.06
     extreme
    -0.06
    æĭ©æł¡
    -0.06
    åĪĿä¸ŃçļĦ
    -0.06
    POSITIVE LOGITS
     training
    0.12
    -training
    0.11
     sessions
    0.11
    åŁ¹è®Ń
    0.11
    training
    0.10
     learning
    0.10
    åŁ¹è®ŃçļĦ
    0.10
     Training
    0.10
    å®ŀæķĪæĢ§
    0.10
     impart
    0.10
    Activations Density 0.536%

    No Known Activations