© 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. 26534
    Prev
    Next
    INDEX
    Explanations

    .TryParse, Source, Date, Rev,Ago, node, $

    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
    nade
    -0.07
    ipay
    -0.06
    еÑģÑĤв
    -0.06
    (ent
    -0.06
    ãĤ¦ãĥī
    -0.06
    atk
    -0.06
    å¯Ħæīĺ
    -0.06
    .ak
    -0.06
    åĩĨå¤ĩ好
    -0.06
    .ap
    -0.06
    POSITIVE LOGITS
     pula
    0.08
    æĥŁä¸Ģ
    0.07
    aq
    0.07
    اشت
    0.07
    .TryParse
    0.07
     Eag
    0.07
    è¾¾åĨħ
    0.07
    amakan
    0.06
    _MINOR
    0.06
    éļħ
    0.06
    Activations Density 0.985%

    No Known Activations