© 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. 19770
    Prev
    Next
    INDEX
    Explanations

    slowing down/stopping

    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
    éĽ¨è¡£
    -0.07
    ë´ī
    -0.07
    leger
    -0.07
    沦
    -0.07
    ONSE
    -0.07
    æ¶Į
    -0.07
    å¯Ħ
    -0.07
    åĽ´çĿĢ
    -0.06
     Chim
    -0.06
    ç½²åIJį
    -0.06
    POSITIVE LOGITS
    åĩıéĢŁ
    0.10
    _deinit
    0.09
    åģľä¸ĭ
    0.08
     braking
    0.08
     gracefully
    0.08
    drop
    0.08
     gradually
    0.08
    åģľä¸ĭæĿ¥
    0.08
    dsn
    0.08
    dsa
    0.08
    Activations Density 0.005%

    No Known Activations