© 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. 62396
    Prev
    Next
    INDEX
    Explanations

    possessive determiners (your, your)

    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
    _compat
    -0.08
     iht
    -0.07
    utable
    -0.07
    ughs
    -0.07
    .asc
    -0.07
    ordia
    -0.07
    ä¸įåľ¨ä¹İ
    -0.07
     Equip
    -0.07
    úb
    -0.07
    uez
    -0.07
    POSITIVE LOGITS
    æ¶Ĥ
    0.07
    <|box_end|>
    0.07
    FM
    0.06
    dg
    0.06
    彦
    0.06
    eph
    0.06
    éĤ£åIJį
    0.06
    lau
    0.06
    fm
    0.06
    ÙħÙĬÙĨ
    0.06
    Activations Density 0.004%

    No Known Activations