© 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. 22321
    Prev
    Next
    INDEX
    Explanations

    firing directions

    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
     growing
    -0.07
    éķ¿å¤§
    -0.07
    ä¸Ģ缴
    -0.07
    adin
    -0.07
    -minus
    -0.06
     growth
    -0.06
    esia
    -0.06
    éŃĶ女
    -0.06
    ä¾¿å®ľ
    -0.06
    顺
    -0.06
    POSITIVE LOGITS
    éĽĨä¸Ńåľ¨
    0.13
    éĽĨä¸Ńäºİ
    0.13
     concentrated
    0.12
    éĽĨä¸ŃçļĦ
    0.12
    åıªåľ¨
    0.11
    éĽĨä¸Ń
    0.11
     peaked
    0.11
    主è¦ģéĽĨä¸Ńåľ¨
    0.10
    Peak
    0.10
     ì§ijì¤ij
    0.10
    Activations Density 0.054%

    No Known Activations