© 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. 18390
    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
    æľīåĪ«
    -0.07
     prem
    -0.07
    çĻ¾å²ģ
    -0.07
    voir
    -0.07
    å¾ĺå¾Ĭ
    -0.06
    borg
    -0.06
    éĽħ
    -0.06
    设计ä¸İ
    -0.06
    çļĦåĬĽéĩı
    -0.06
    odem
    -0.06
    POSITIVE LOGITS
    elihood
    0.07
    ewood
    0.07
    _DIAG
    0.07
    amenta
    0.07
    lad
    0.07
    ERGY
    0.06
    illant
    0.06
    erk
    0.06
    IANA
    0.06
    ido
    0.06
    Activations Density 0.000%

    No Known Activations