© 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. 43972
    Prev
    Next
    INDEX
    Explanations

    effect of actions or treatments

    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
    人ä¸Ģ
    -0.08
    ander
    -0.07
    说æĺİäºĨ
    -0.07
    éĢļè¿ĩè¿Ļ个
    -0.07
    ä¸ĢæĹ¦è¢«
    -0.07
    دÙĦ
    -0.07
    æĶ¿çŃĸæĶ¯æĮģ
    -0.07
    æľªæĿ¥åıijå±ķ
    -0.07
    èĩªæĪij管çIJĨ
    -0.07
    Ñħов
    -0.07
    POSITIVE LOGITS
    åİŁæĿ¥çļĦ
    0.09
    åİŁæľīçļĦ
    0.09
    åıĺæĪIJä¸Ģ个
    0.09
    åİŁæľ¬çļĦ
    0.09
    æĸ°çļĦ
    0.08
    使
    0.08
    åİŁæľī
    0.08
     changes
    0.08
    åİŁæľ¬
    0.08
    æĶ¹åıĺ
    0.08
    Activations Density 0.049%

    No Known Activations