© 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. 16764
    Prev
    Next
    INDEX
    Explanations

    new Custom

    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
    ene
    -0.06
    pkg
    -0.06
    ign
    -0.06
    w
    -0.06
    eut
    -0.05
    be
    -0.05
    rv
    -0.05
     Lang
    -0.05
    spec
    -0.05
     spec
    -0.05
    POSITIVE LOGITS
    opleft
    0.09
    ucch
    0.09
    agd
    0.09
    ÃŃcula
    0.08
    noz
    0.08
    åĨįæİ¥åĨį
    0.08
     AFP
    0.08
    ripper
    0.08
    ziu
    0.08
    uyến
    0.08
    Activations Density 0.037%

    No Known Activations