© 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. 51452
    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
    aled
    -0.08
    kopf
    -0.07
    æīĵæĪIJ
    -0.07
    æľīåķ¥
    -0.07
    efined
    -0.07
    ymoon
    -0.07
    ijn
    -0.06
    åķ¥
    -0.06
    çµ®
    -0.06
     Mic
    -0.06
    POSITIVE LOGITS
    @m
    0.08
    失
    0.07
    /commons
    0.07
    teis
    0.07
    èĽī
    0.07
    æľ¬å±Ĭ
    0.07
    çļĦåĬĽéĩı
    0.07
    esm
    0.07
    ĥ½
    0.07
    acco
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.