© 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. 13344
    Prev
    Next
    INDEX
    Explanations

    variable declarations and assignments

    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
    为è¾ħ
    -0.07
    .mkdir
    -0.06
    oni
    -0.06
     há»ĵn
    -0.06
    æķ·
    -0.06
    -
    -0.06
    ervis
    -0.06
    actable
    -0.06
    éĢĤçĶ¨æ³ķå¾ĭ
    -0.06
     Faro
    -0.05
    POSITIVE LOGITS
    AndGet
    0.08
    andum
    0.08
    mans
    0.07
    anness
    0.07
    akon
    0.07
    isko
    0.07
    é²²
    0.07
    nene
    0.07
    omite
    0.07
    дела
    0.07
    Activations Density 0.008%

    No Known Activations