© 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. 16712
    Prev
    Next
    INDEX
    Explanations

    is or was followed by 'a' or 'an'

    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
    tera
    -0.10
    à¸į
    -0.08
    çĻ¾è®¡
    -0.08
    ãģ²ãĤį
    -0.08
    lick
    -0.08
    abled
    -0.08
    ÑİÑģÑĮ
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    gom
    -0.08
    Ñİз
    -0.08
    POSITIVE LOGITS
    /is
    0.07
    onale
    0.06
     #=>
    0.06
    amoto
    0.06
    ’
    0.06
     ax
    0.06
    æ¯ĶæĪij
    0.06
    ory
    0.05
     ‘
    0.05
    _iff
    0.05
    Activations Density 0.149%

    No Known Activations