© 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. 50749
    Prev
    Next
    INDEX
    Explanations

    list item separators or answers

    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
    oha
    -0.07
    اÙģÙĬØ©
    -0.07
    æīĢå±ŀè¡Įä¸ļ
    -0.07
    hift
    -0.07
    ilu
    -0.07
    idget
    -0.07
    -conf
    -0.07
    ROADCAST
    -0.07
    -paid
    -0.07
    ç±³é«ĺ
    -0.07
    POSITIVE LOGITS
    ase
    0.09
    apan
    0.08
    utdown
    0.07
    ccione
    0.07
    ases
    0.07
    åĩıéĩı
    0.07
    ihn
    0.06
    ament
    0.06
    èĭį
    0.06
    è¾ĥ大çļĦ
    0.06
    Activations Density 0.026%

    No Known Activations