© 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. 42655
    Prev
    Next
    INDEX
    Explanations

    experimental results and observations

    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
    quat
    -0.08
    ARNING
    -0.08
    INESS
    -0.08
    resh
    -0.08
    æŀ¶æŀĦ
    -0.07
    Comple
    -0.07
     Sinon
    -0.07
    å¾Ĺ罪
    -0.07
     Mansion
    -0.07
    ç¿°
    -0.07
    POSITIVE LOGITS
    å®ŀæµĭ
    0.11
     data
    0.09
    äºĭå®Ł
    0.09
    facts
    0.09
    äºĭå®ŀ
    0.08
    å®ŀäºĭ
    0.08
     observations
    0.08
     reality
    0.08
     faits
    0.08
     reales
    0.08
    Activations Density 0.091%

    No Known Activations