© 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. 45897
    Prev
    Next
    INDEX
    Explanations

    OH radical

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ä¸ĭå¿ĥæĿ¥
    -0.07
    Ø·Ùģ
    -0.06
    çĸ®
    -0.06
    T
    -0.06
    pot
    -0.06
    åĬŀåħ¬åİħ
    -0.06
    ife
    -0.06
    åİŁåĽłåľ¨äºİ
    -0.06
    ividual
    -0.06
    бÑĢе
    -0.06
    POSITIVE LOGITS
    ehme
    0.08
    icole
    0.08
    çī¹å°Ķ
    0.08
    æľ¬ç¤¾
    0.08
    IELDS
    0.08
    à®Łà¯Ī
    0.08
    blers
    0.08
    laps
    0.07
    รี
    0.07
    acker
    0.07
    Activations Density 0.001%

    No Known Activations