© 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. 15791
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    inge
    -0.08
    mi
    -0.08
    èĩªçĶ±
    -0.07
    mit
    -0.06
    atory
    -0.06
    ju
    -0.06
    mis
    -0.06
     Bat
    -0.06
    以ä¸Ĭ
    -0.06
    éģ¥
    -0.06
    POSITIVE LOGITS
    aho
    0.08
    åħĭèIJ¨æĸ¯
    0.08
    ìĪŃ
    0.08
    buk
    0.08
    ARGS
    0.08
    tul
    0.08
    urÄĥ
    0.07
     terrest
    0.07
    -output
    0.07
    çīĩçīĩ
    0.07
    Activations Density 0.000%

    No Known Activations