© 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. 46949
    Prev
    Next
    INDEX
    Explanations

    physics and dynamics

    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
    .twitch
    -0.08
    对å¾ħ
    -0.08
    fos
    -0.08
    ÃīT
    -0.07
     Checked
    -0.07
    جÙĦ
    -0.07
    ailer
    -0.07
    åªļ
    -0.07
    æ¯ı天éĥ½æľī
    -0.07
    heim
    -0.07
    POSITIVE LOGITS
     constrained
    0.08
     governed
    0.07
     redistribute
    0.07
    _restrict
    0.07
    ucht
    0.07
    ç¦ģ
    0.06
     restricted
    0.06
    éģį
    0.06
    å±Ģéķ¿
    0.06
    restricted
    0.06
    Activations Density 0.071%

    No Known Activations