© 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. 18391
    Prev
    Next
    INDEX
    Explanations

    integers and numbers

    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
    åħ¨å¤©åĢĻ
    -0.07
    inho
    -0.07
    é«ĺçħ§
    -0.07
    -cap
    -0.07
     Viale
    -0.07
    åħ¨è¿ĩç¨ĭ
    -0.06
    å°ĶèĴĻ
    -0.06
     rdr
    -0.06
     ole
    -0.06
    veren
    -0.06
    POSITIVE LOGITS
     integer
    0.11
    æķ´æķ°
    0.11
     integers
    0.11
    integer
    0.10
    Integer
    0.09
    (Integer
    0.09
    (integer
    0.09
     Integer
    0.09
    _Integer
    0.08
    egers
    0.08
    Activations Density 0.006%

    No Known Activations