© 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. 29487
    Prev
    Next
    INDEX
    Explanations

    asking about a problem

    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
    /oct
    -0.08
    inol
    -0.07
    werkt
    -0.07
    çīĩä¸Ń
    -0.07
    å°ijçļĦ
    -0.07
    kel
    -0.07
    åĢļ
    -0.07
    inak
    -0.07
    ibles
    -0.07
     Portions
    -0.07
    POSITIVE LOGITS
    veau
    0.08
    æĺ¯è®©
    0.08
    emme
    0.08
     definition
    0.07
    name
    0.07
     name
    0.07
    è¦ģæ±Ĥ被åijĬ
    0.07
    å°±æĺ¯æĬĬ
    0.07
    vap
    0.07
    ette
    0.07
    Activations Density 0.005%

    No Known Activations