© 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. 28103
    Prev
    Next
    INDEX
    Explanations

    accessing files

    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
    .Tools
    -0.08
    trut
    -0.08
    thouse
    -0.06
    èĨĺ
    -0.06
    Ñĩи
    -0.06
    é¹°
    -0.06
    åĭĴæĸ¯
    -0.06
    ãĥ¥ãĥ¼
    -0.06
     trough
    -0.06
    éĽĦé¹°
    -0.06
    POSITIVE LOGITS
    顾åIJįæĢĿä¹ī
    0.10
    èģĶæĴŃ
    0.08
    ษ
    0.08
    ç»°
    0.08
    ä»ķæĸ¹
    0.07
    apol
    0.07
    gın
    0.07
    çĶ±æĸ¼
    0.07
    pNet
    0.06
    èĻ½çĦ¶ä¸įæĺ¯
    0.06
    Activations Density 0.117%

    No Known Activations