© 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. 57915
    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
    sche
    -0.08
    snap
    -0.08
    .setBackgroundColor
    -0.07
    éŨåħ³
    -0.07
    urch
    -0.07
    .removeAttribute
    -0.07
    dor
    -0.07
     Giovan
    -0.07
    ibri
    -0.07
     اÙĦÙģض
    -0.07
    POSITIVE LOGITS
    0.07
    ç¯ĩ
    0.07
    0.06
     deprecated
    0.06
    ude
    0.06
    ing
    0.06
    åģī
    0.06
    ity
    0.06
    inge
    0.06
    utt
    0.06
    Activations Density 0.000%

    No Known Activations