© 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. 38415
    Prev
    Next
    INDEX
    Explanations

    teaching yourself

    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
    lider
    -0.07
    æľĶ
    -0.07
    rov
    -0.07
    wor
    -0.07
    avana
    -0.07
    çĿ¦
    -0.06
    mux
    -0.06
    phant
    -0.06
    avia
    -0.06
    审åĪ¤åijĺ
    -0.06
    POSITIVE LOGITS
    [table
    0.07
     prévoir
    0.07
    åĸ½
    0.07
     Peker
    0.07
    è°Īä¸įä¸Ĭ
    0.07
    ä¸įä¼ļæĺ¯
    0.07
    zeige
    0.07
     saying
    0.06
    atine
    0.06
     TABLE
    0.06
    Activations Density 0.021%

    No Known Activations