© 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. 46138
    Prev
    Next
    INDEX
    Explanations

    integer and discrete values

    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
    åħĭåħ°
    -0.11
    ней
    -0.09
    ãģ»ãģĨ
    -0.08
    raga
    -0.08
    resso
    -0.08
    丽èİİ
    -0.08
    éĩij森
    -0.08
     Normandie
    -0.08
    SIDE
    -0.08
    .beta
    -0.08
    POSITIVE LOGITS
     integer
    0.11
    æķ´æķ°
    0.10
    integer
    0.10
     discrete
    0.10
    Integer
    0.09
    æķ´
    0.09
     granularity
    0.08
     Integer
    0.08
    _integer
    0.07
     INTEGER
    0.07
    Activations Density 0.008%

    No Known Activations