© 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. 29568
    Prev
    Next
    INDEX
    Explanations

    verbs indicating completion or explanation after an action

    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
    ÛĮتÛĮ
    -0.08
    penas
    -0.08
    è¿ĻäºĽéĥ½
    -0.08
    ÛĮÙĨÛĮ
    -0.08
    äºĨ大éĩıçļĦ
    -0.07
    ତ
    -0.07
    äºĨ好
    -0.07
    éĤ£ä»½
    -0.07
    лека
    -0.07
    åı¸ä»¤éĥ¨
    -0.07
    POSITIVE LOGITS
    /use
    0.07
     using
    0.07
     by
    0.07
     be
    0.06
    opsis
    0.06
    ANCH
    0.06
    uchen
    0.06
    ÙĤاÙĦ
    0.06
     via
    0.06
    ERGY
    0.06
    Activations Density 0.079%

    No Known Activations