© 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. 19382
    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
    liku
    -0.06
    ex
    -0.06
    ä¾ĭ
    -0.06
    åĽ¾ç¤º
    -0.06
    ures
    -0.06
    (\'
    -0.06
    飦å°Ķ
    -0.06
     or
    -0.06
    ork
    -0.06
     Champ
    -0.06
    POSITIVE LOGITS
    æģ¯çļĦ
    0.08
    (OP
    0.08
    orris
    0.08
    kla
    0.08
    ç¾²
    0.08
    igon
    0.08
    _reserved
    0.08
    nid
    0.07
    ovement
    0.07
    è²
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.