© 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. 24701
    Prev
    Next
    INDEX
    Explanations

    super-symmetric

    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
    erso
    -0.10
    HELL
    -0.08
    -Series
    -0.08
    æī£çķĻ
    -0.08
    åĩłå¤©çļĦ
    -0.08
    /qt
    -0.08
    enarios
    -0.08
    iales
    -0.08
    TRIB
    -0.08
     efficac
    -0.08
    POSITIVE LOGITS
    æĿĸ
    0.08
     Prop
    0.06
    èįīåľ°ä¸Ĭ
    0.06
    Prop
    0.06
    ariant
    0.06
    emi
    0.06
     Green
    0.06
    ulous
    0.06
    ì¶Ķ
    0.06
     tw
    0.06
    Activations Density 0.005%

    No Known Activations