© 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. 61314
    Prev
    Next
    INDEX
    Explanations

    following "concept" or "data"

    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
    çļĦä¸Ģç§į
    -0.08
    è¿Ļæł·ä¸Ģç§į
    -0.08
    å°±éĤ£ä¹Ī
    -0.07
    常说çļĦ
    -0.07
    çļĦä¸Ģ種
    -0.07
    éĿŀ常å¤ļ
    -0.07
    çļĦä¸Ģ件äºĭ
    -0.07
    çļĦéĩįè¦ģéĢĶå¾Ħ
    -0.07
    éĩįçĶŁä¹ĭ
    -0.07
    å¦Ĥä¸ĭ
    -0.07
    POSITIVE LOGITS
     azért
    0.09
    çļĦä¸ĢåĪĩéĥ½
    0.08
    æīįæĺ¯
    0.08
    æĺ¯æĪij
    0.08
    åı¯æĺ¯æĪij
    0.08
     represents
    0.08
    æīįæĺ¯çľŁæŃ£çļĦ
    0.08
    羣å®ŀæĢ§è´Łè´£
    0.08
    æĺ¯æľĢ
    0.08
    efs
    0.08
    Activations Density 0.640%

    No Known Activations