© 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. 14874
    Prev
    Next
    INDEX
    Explanations

    html tag closures

    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
    à®ŀ
    -0.09
    oura
    -0.08
    éĺħè¯»æľ¬æĸĩåīį
    -0.08
    çĤ¹åĩ»éĺħ读åİŁæĸĩ
    -0.08
    转载请
    -0.08
    å¾Ĺèµ·
    -0.08
    å¦ĤæľŁ
    -0.08
    strup
    -0.08
    äck
    -0.07
    eneg
    -0.07
    POSITIVE LOGITS
    ```
    0.07
     -
    0.07
    éĥİ
    0.06
    å§Ĩæĸ¯
    0.06
     pass
    0.06
    æ±ī
    0.06
    unea
    0.06
    "
    0.06
    ÑĢиев
    0.06
     work
    0.06
    Activations Density 0.352%

    No Known Activations