© 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. 9853
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns like its, her

    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
    ed
    -0.11
    åľ¨æĹģè¾¹
    -0.08
    åľ¨
    -0.07
    esian
    -0.07
    al
    -0.07
    zion
    -0.07
    ized
    -0.07
    incontro
    -0.06
    ation
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    POSITIVE LOGITS
    /her
    0.12
     own
    0.11
    lef
    0.10
    ergestellt
    0.10
    иÑİ
    0.10
    SELF
    0.10
     latter
    0.10
     usual
    0.09
    ä¸įçĦ¶
    0.09
    ä¿©
    0.09
    Activations Density 0.006%

    No Known Activations