© 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. 20114
    Prev
    Next
    INDEX
    Explanations

    .android code paths

    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
    åĿIJäºĨ
    -0.07
    poi
    -0.07
    /documents
    -0.07
    éĵĥ
    -0.07
    çĶ±ä¼ģä¸ļ
    -0.07
    è¿ĩå¢ĥ
    -0.06
    .decor
    -0.06
    {}]
    -0.06
    è¿Ļä¸ªä¸ľè¥¿
    -0.06
    çĶ±åħ¬åı¸
    -0.06
    POSITIVE LOGITS
    çļĦ主
    0.08
    æľī责任å¿ĥ
    0.07
    ÑĦей
    0.07
    עת
    0.07
    Sensitive
    0.07
    _HERE
    0.07
    _glob
    0.07
    .this
    0.07
    åīįè¿°
    0.07
    ç´§è¦ģ
    0.07
    Activations Density 0.332%

    No Known Activations