© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26805
    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
    ç¬ijäºĨèµ·æĿ¥
    -0.07
    ancement
    -0.07
    manship
    -0.07
     íķ¨
    -0.06
     vraiment
    -0.06
    igneur
    -0.06
    æĬĬäºĭæĥħ
    -0.06
    ahre
    -0.06
    ueux
    -0.06
    fication
    -0.06
    POSITIVE LOGITS
    -del
    0.08
     yourselves
    0.08
    peg
    0.08
     برس
    0.08
    Reached
    0.07
    çŁ¥å¿ĥ
    0.07
    çĢ
    0.07
    éĺ³æĺ¥
    0.07
    <![
    0.07
    æľīä½Ļ
    0.07
    Activations Density 0.000%

    No Known Activations