© 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. 19661
    Prev
    Next
    INDEX
    Explanations

    DisplayName QUOTE

    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
    an
    -0.08
    n
    -0.06
    ®
    -0.06
    us
    -0.06
    ec
    -0.06
     aran
    -0.06
    _CFG
    -0.05
    em
    -0.05
     зан
    -0.05
    on
    -0.05
    POSITIVE LOGITS
    fillable
    0.08
    _iters
    0.08
    ivée
    0.08
    scratch
    0.08
    好åij¢
    0.08
    _para
    0.07
    æĻ
    0.07
    vem
    0.07
    ffee
    0.07
    ampoo
    0.07
    Activations Density 0.003%

    No Known Activations