© 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. 32113
    Prev
    Next
    INDEX
    Explanations

    carbon, venting, matting, socketing, tendering, mineralization, commercialization

    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
    ivamente
    -0.10
    itamente
    -0.09
    ALLY
    -0.08
    ativamente
    -0.08
    abilmente
    -0.07
    ensively
    -0.07
    ÑģÑĤÑĮ
    -0.07
    USES
    -0.07
     dinas
    -0.07
    AMENTE
    -0.07
    POSITIVE LOGITS
    ing
    0.24
    ed
    0.19
    ation
    0.16
    ization
    0.16
    ting
    0.15
    ings
    0.14
    ning
    0.14
    ingin
    0.13
    ification
    0.13
    izing
    0.13
    Activations Density 1.621%

    No Known Activations