© 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. 3968
    Prev
    Next
    INDEX
    Explanations

    autobiographer

    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
     hol
    -0.06
     Bang
    -0.06
     emot
    -0.06
     bots
    -0.06
    èĥľäºİ
    -0.05
    stro
    -0.05
     Bund
    -0.05
    icons
    -0.05
    airs
    -0.05
    ụ
    -0.05
    POSITIVE LOGITS
    abt
    0.08
    entif
    0.08
    饨
    0.08
    ftype
    0.08
    ÑĢÑĤи
    0.08
     вÑĢе
    0.08
    ramework
    0.08
    eor
    0.07
     поÑģÑĤанов
    0.07
    eneg
    0.07
    Activations Density 0.092%

    No Known Activations