© 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. 63645
    Prev
    Next
    INDEX
    Explanations

    endings like able, ible, ability

    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
    ÅĻe
    -0.09
    اظ
    -0.08
    뾨
    -0.07
    ovÄĽ
    -0.07
    hydr
    -0.07
    ļľ
    -0.07
    转载请
    -0.07
    ários
    -0.07
    ificates
    -0.07
    审é¢ĺ
    -0.07
    POSITIVE LOGITS
    able
    0.22
    ABLE
    0.17
    ability
    0.16
    ible
    0.16
    izable
    0.14
    ably
    0.13
    isable
    0.12
    gable
    0.12
    iable
    0.12
    bable
    0.12
    Activations Density 0.130%

    No Known Activations