© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61790
    Prev
    Next
    INDEX
    Explanations

    JSON-like structures

    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
    éļĪ
    -0.08
    åħ³æĿij
    -0.08
    ech
    -0.08
    ċ
    -0.08
    üssen
    -0.07
    SOR
    -0.07
    -icons
    -0.07
    acon
    -0.07
    ãģĭãģ¤
    -0.07
    alic
    -0.07
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.07
    ä½³
    0.06
     Crossing
    0.06
     fil
    0.06
     ingen
    0.06
    беÑĤ
    0.06
    åĩºäºº
    0.06
    outu
    0.06
     herself
    0.06
    irt
    0.06
    Activations Density 0.002%

    No Known Activations