© 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. 45328
    Prev
    Next
    INDEX
    Explanations

    dense, total, symmetric, power, join, pair

    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
    wai
    -0.08
    Ñģпи
    -0.08
    ylan
    -0.07
    ommel
    -0.07
    å®Ŀé¾Ļ
    -0.07
    读课æĸĩ
    -0.07
    anze
    -0.07
    .TryParse
    -0.07
    adal
    -0.07
    boss
    -0.07
    POSITIVE LOGITS
    çĥĪ
    0.07
    å¯Ĩ
    0.07
    except
    0.07
    ç¨ĭ度
    0.07
     except
    0.07
    osaur
    0.07
     dense
    0.07
    /full
    0.07
    dense
    0.07
     ÃĤn
    0.07
    Activations Density 0.006%

    No Known Activations