© 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. 50498
    Prev
    Next
    INDEX
    Explanations

    a followed by noun

    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
    rastructure
    -0.08
     behalf
    -0.08
    enerate
    -0.08
    ÑĢÑıдÑĥ
    -0.07
    O
    -0.07
    ilename
    -0.07
    E
    -0.07
    ẵn
    -0.07
    è¡
    -0.07
    еÑĢж
    -0.07
    POSITIVE LOGITS
    orem
    0.16
    alborg
    0.10
    ories
    0.10
    comings
    0.10
    oretical
    0.08
    usterity
    0.08
    dept
    0.08
    byss
    0.08
    enes
    0.08
    verages
    0.08
    Activations Density 0.411%

    No Known Activations