© 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. 47081
    Prev
    Next
    INDEX
    Explanations

    left, right, or top positions

    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
    ire
    -0.07
    ÏĦεÏħ
    -0.07
    rau
    -0.07
    irn
    -0.07
    ss
    -0.06
    ppo
    -0.06
    ship
    -0.06
     Rae
    -0.06
    rud
    -0.06
    ׼×ķת
    -0.06
    POSITIVE LOGITS
    §
    0.08
    æ±ĩéĽĨäºĨ
    0.08
    åĬ
    0.08
    ourcem
    0.07
    Ĺ
    0.07
    -letter
    0.07
    zysta
    0.07
    addock
    0.07
    UpDown
    0.07
    abbrev
    0.07
    Activations Density 0.052%

    No Known Activations