© 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. 13821
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by actions or states

    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
    tery
    -0.08
    iliz
    -0.08
    Ùĭ
    -0.07
    æħ°
    -0.07
    Unchecked
    -0.07
    erva
    -0.07
    欣
    -0.07
    оÑĢÑı
    -0.06
    gnore
    -0.06
    -INF
    -0.06
    POSITIVE LOGITS
    /her
    0.09
    zelf
    0.09
    è¿Ļæł·åģļ
    0.07
    ؤÙĦاء
    0.07
    æī¾åĪ°èĩªå·±
    0.07
    è¿Ļéĥ½æĺ¯
    0.07
    adel
    0.07
    çŃīåIJĦ
    0.07
    åı¯æĺ¯ä¸Ģ
    0.06
    ader
    0.06
    Activations Density 0.736%

    No Known Activations