© 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. 64399
    Prev
    Next
    INDEX
    Explanations

    pronouns her/his/he

    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
    juh
    -0.09
    æĪijè¦ģæĬķè¯ī
    -0.08
    etag
    -0.08
    åĴĮ幸ç¦ı
    -0.08
    logan
    -0.08
    /background
    -0.07
    Tunes
    -0.07
    ugal
    -0.07
    -force
    -0.07
     Kasat
    -0.07
    POSITIVE LOGITS
    çİĩè¾¾åĪ°
    0.07
    %S
    0.07
    ī
    0.06
    ól
    0.06
    omb
    0.06
    astre
    0.06
    æ¹
    0.06
     lump
    0.06
     Tib
    0.06
    caps
    0.06
    Activations Density 0.893%

    No Known Activations