© 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. 20015
    Prev
    Next
    INDEX
    Explanations

    citations followed by numbers

    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
    天çĶŁçļĦ
    -0.07
    dden
    -0.07
    achs
    -0.07
    werp
    -0.07
    defs
    -0.07
    ä¸įæĬĬ
    -0.07
    unner
    -0.07
    Ö¼
    -0.07
    åįĵ
    -0.06
     zero
    -0.06
    POSITIVE LOGITS
    accuracy
    0.08
    åį¯
    0.07
     research
    0.07
    liers
    0.07
     accuracy
    0.07
     Royal
    0.07
    åĥļ
    0.06
    pect
    0.06
    æ±²
    0.06
    AGES
    0.06
    Activations Density 0.067%

    No Known Activations