© 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. 56143
    Prev
    Next
    INDEX
    Explanations

    words ending in -er, -ater, -er, -ists

    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
    ARIO
    -0.07
    åįĹè¡Ĺ
    -0.07
    åľ¨èº«
    -0.07
    rir
    -0.06
    åĮĸ管çIJĨ
    -0.06
    rt
    -0.06
    erty
    -0.06
    _based
    -0.06
     ownership
    -0.06
    ond
    -0.06
    POSITIVE LOGITS
     who
    0.12
     whose
    0.12
    whose
    0.12
    ä»¬åľ¨
    0.11
    à¹ģà¸¥à¸°à¸ľà¸¹à¹ī
    0.11
     extraordinaire
    0.11
     whom
    0.10
    innen
    0.10
    åħ¼
    0.10
    who
    0.10
    Activations Density 0.971%

    No Known Activations