© 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. 23981
    Prev
    Next
    INDEX
    Explanations

    ---

    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
    acific
    -0.09
    awas
    -0.09
    zey
    -0.08
    anye
    -0.08
    ibre
    -0.08
    ----------------------------------------------------------------------
    -0.08
    oulos
    -0.08
    patible
    -0.08
    Referensi
    -0.08
    moire
    -0.08
    POSITIVE LOGITS
    er
    0.07
    udio
    0.07
    en
    0.07
    alom
    0.07
    este
    0.07
    ive
    0.07
    usting
    0.06
    æijĺèĩª
    0.06
    ©
    0.06
    enberg
    0.06
    Activations Density 0.092%

    No Known Activations