© 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. 49796
    Prev
    Next
    INDEX
    Explanations

    numerical or categorical labels

    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
    __.__
    -0.07
    èĩªè´£
    -0.07
    اÙģ
    -0.06
    terie
    -0.06
    论
    -0.06
    avers
    -0.06
    dom
    -0.06
    annis
    -0.06
    oue
    -0.06
    èªī
    -0.06
    POSITIVE LOGITS
    è¿Ļ个æķ°åŃĹ
    0.09
    代表çĿĢ
    0.08
    代表
    0.08
    åı·
    0.08
    ë²Ī
    0.08
     Num
    0.08
    Ordinal
    0.07
    Categ
    0.07
    åı·ä¸º
    0.07
     angka
    0.07
    Activations Density 0.169%

    No Known Activations