© 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. 19104
    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
    ķĮ
    -0.07
    ince
    -0.07
    ambo
    -0.07
    ToRemove
    -0.07
    eza
    -0.07
    åįłåħ¨åĽ½
    -0.06
     administr
    -0.06
    ä½ĵéŃĦ
    -0.06
    é»Ħ页
    -0.06
    .signals
    -0.06
    POSITIVE LOGITS
    åĪ©çī©
    0.08
    .constructor
    0.07
    ivec
    0.07
    _DP
    0.07
    å±±é«ĺ
    0.07
    çŁ³æ£ī
    0.07
    å±±éĩİ
    0.07
    trin
    0.06
    attern
    0.06
    ä¸ĢåºĶ
    0.06
    Activations Density 0.000%

    No Known Activations