© 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. 43576
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in code/markup

    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
    iba
    -0.08
    éĩĩ
    -0.08
    ä¸īåįģåħŃ
    -0.08
    isd
    -0.07
    æ®ĸ
    -0.07
    bacher
    -0.06
    å®Ĺ主
    -0.06
    lager
    -0.06
    isma
    -0.06
     iste
    -0.06
    POSITIVE LOGITS
    endr
    0.08
     sang
    0.08
    .sourceforge
    0.08
    inaan
    0.08
    idth
    0.08
    edImage
    0.07
    edList
    0.07
    endid
    0.07
    dba
    0.07
    ؤÙĦ
    0.07
    Activations Density 0.032%

    No Known Activations