© 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. 31044
    Prev
    Next
    INDEX
    Explanations

    adjective suffixes like y, ey, py, hy, ery

    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
    ppure
    -0.10
    ers
    -0.10
    ivol
    -0.10
    erior
    -0.09
    äºĨ对
    -0.09
    igli
    -0.09
    æĢ§åľ°
    -0.09
    ovic
    -0.09
    еÑĩ
    -0.09
    ÑĬÑĤ
    -0.09
    POSITIVE LOGITS
    NESS
    0.11
    ness
    0.10
    zza
    0.09
    -looking
    0.08
    keiten
    0.08
    fication
    0.08
    -eyed
    0.08
    ields
    0.08
     enough
    0.08
    ä¸įåłª
    0.07
    Activations Density 0.203%

    No Known Activations