© 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. 23682
    Prev
    Next
    INDEX
    Explanations

    of approximately

    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
    æľīè¾ĥ强çļĦ
    -0.07
    ä¹ĭéĹ´åŃĺåľ¨
    -0.07
    æīĢæľīçļĦ
    -0.07
    åģļ为
    -0.07
    bjerg
    -0.07
    æĤ´
    -0.06
    ä¹ĭéĹ´æľī
    -0.06
    ç»Ĩå¿ĥçļĦ
    -0.06
     tartal
    -0.06
    aggi
    -0.06
    POSITIVE LOGITS
    untime
    0.07
    agara
    0.07
    oyer
    0.07
    essar
    0.07
    olto
    0.07
    ewart
    0.07
    //{{
    0.06
    ouve
    0.06
    /configuration
    0.06
    olation
    0.06
    Activations Density 0.166%

    No Known Activations