© 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. 2189
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    arat
    -0.07
    OrCreate
    -0.07
    zel
    -0.07
    åIJĦæĸ¹
    -0.07
    å±Ģéķ¿
    -0.07
    ç¼Ńç»ķ
    -0.07
    implicit
    -0.07
    atable
    -0.07
    ä¹Ŀæ±Ł
    -0.07
    eria
    -0.07
    POSITIVE LOGITS
    uth
    0.07
    éĺ¿ç±³
    0.07
    åħ±åĴĮ
    0.07
     Betro
    0.06
    å½Ī
    0.06
    _TERM
    0.06
    ad
    0.06
    amak
    0.06
    äºĨæĪijçļĦ
    0.06
    ike
    0.06
    Activations Density 0.051%

    No Known Activations