© 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. 45098
    Prev
    Next
    INDEX
    Explanations

    horizontal branch

    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
    娲
    -0.07
    riot
    -0.07
    rows
    -0.06
    åĤħ
    -0.06
    à¹Ħà¸Ĥà¹ī
    -0.06
    assar
    -0.06
    alien
    -0.06
    OLS
    -0.06
    人çļĦ
    -0.06
     cÆ°á»Ŀng
    -0.06
    POSITIVE LOGITS
    oad
    0.09
    ÙĪÙĦÙĬ
    0.08
    aname
    0.08
    otre
    0.08
    ı
    0.07
    ritti
    0.07
    accio
    0.07
    fase
    0.07
    积èĵĦ
    0.07
    迹
    0.07
    Activations Density 0.002%

    No Known Activations