© 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. 13818
    Prev
    Next
    INDEX
    Explanations

    third, fifth, or ninth

    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
    entif
    -0.08
    ocre
    -0.07
    incare
    -0.07
    éĥ¨å°±
    -0.07
    人äºĨ
    -0.07
    nds
    -0.07
    __.__
    -0.07
     بÙIJÙĩÙIJ
    -0.07
    noop
    -0.07
    εδ
    -0.07
    POSITIVE LOGITS
    åįķçĭ¬
    0.07
    walls
    0.07
    issa
    0.07
    ilag
    0.06
    èī¯
    0.06
     Swagger
    0.06
    说è°İ
    0.06
    ãģ´
    0.06
    tri
    0.06
     pylint
    0.06
    Activations Density 0.329%

    No Known Activations