© 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. 51101
    Prev
    Next
    INDEX
    Explanations

    fly or related to flight

    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
    .fun
    -0.08
    .dev
    -0.08
    appropri
    -0.07
    elmi
    -0.07
    ilton
    -0.07
    åıĪåĪ°
    -0.07
    iver
    -0.07
     wholes
    -0.07
    çIJĨ论水平
    -0.07
    veen
    -0.07
    POSITIVE LOGITS
    çĬ¶æĢģçļĦ
    0.07
    éĤ¯
    0.07
    åĪ©çļĦ
    0.07
    á»ijng
    0.07
    _basename
    0.07
    ç¤İ
    0.07
    常驻
    0.06
    ülü
    0.06
    åĪ©
    0.06
    ucks
    0.06
    Activations Density 0.079%

    No Known Activations