© 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. 58523
    Prev
    Next
    INDEX
    Explanations

    null, none, nil

    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
    annya
    -0.09
    nt
    -0.09
    etz
    -0.07
    åĪ«ç¦»
    -0.07
     himself
    -0.07
    erv
    -0.07
    anni
    -0.07
    боле
    -0.07
    å°ıåŃIJ
    -0.07
    ntl
    -0.07
    POSITIVE LOGITS
    PointerException
    0.10
    kontakte
    0.07
    WithTag
    0.07
    ingue
    0.07
    idad
    0.07
    blas
    0.07
    ibat
    0.07
    uminio
    0.07
    Ľ
    0.07
    zinha
    0.07
    Activations Density 0.037%

    No Known Activations