© 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. 27315
    Prev
    Next
    INDEX
    Explanations

    position followed by number

    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
     Rad
    -0.09
    ÙĨدÙĩ
    -0.07
     Fre
    -0.07
    عÙģ
    -0.07
    çĶļèĩ³æľī
    -0.07
    ibert
    -0.07
    .Rad
    -0.06
    enza
    -0.06
    ycl
    -0.06
    羣å®ŀæĢ§è´Łè´£
    -0.06
    POSITIVE LOGITS
    ichi
    0.08
    ç¼ĸåı·
    0.08
    pers
    0.07
    æ³ķåħ°åħĭç¦ı
    0.07
     numbered
    0.07
    resi
    0.07
     án
    0.07
    lettes
    0.07
    ÃŃas
    0.07
     pháºŃn
    0.06
    Activations Density 0.014%

    No Known Activations