© 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. 12723
    Prev
    Next
    INDEX
    Explanations

    for each

    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
    è¿Ļä¸İ
    -0.07
    <|box_end|>
    -0.07
    uju
    -0.07
    à¸ķà¹Ī
    -0.07
    çĨŁèĥ½
    -0.07
    ORTE
    -0.07
    QE
    -0.06
    æĢİ
    -0.06
    à°ķà±ģ
    -0.06
    имÑĥ
    -0.06
    POSITIVE LOGITS
    èĢĮè¨Ģ
    0.08
    èµ·è§ģ
    0.08
     instance
    0.07
     overe
    0.07
    ìĸ´ìĦľ
    0.07
    Ñī
    0.07
    ledo
    0.07
     Instance
    0.07
    æĪij们èĥ½å¤Ł
    0.07
    ãģ¨ãģĦãģ£ãģ¦
    0.07
    Activations Density 0.011%

    No Known Activations