© 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. 32824
    Prev
    Next
    INDEX
    Explanations

    `B` or name

    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
    ró
    -0.07
    çľģå§Ķ书记
    -0.07
    ä¸Ģä¸įå°ıå¿ĥ
    -0.07
    èĢĥå®ĺ
    -0.07
     Instant
    -0.07
    gnore
    -0.07
     Bá
    -0.06
    é«ĺåľ°
    -0.06
    åħ¬åı¸èij£äºĭéķ¿
    -0.06
    éch
    -0.06
    POSITIVE LOGITS
     override
    0.09
    èģĮè´£
    0.09
    çļĦèģĮè´£
    0.08
    éĩį大äºĭ项
    0.08
     conven
    0.08
    就该
    0.08
    æľīäºĭ
    0.08
     responsibilities
    0.08
    èģĮèĥ½
    0.08
     responsibility
    0.08
    Activations Density 0.009%

    No Known Activations