© 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. 47480
    Prev
    Next
    INDEX
    Explanations

    dentate or chelating agents

    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
    verity
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    cies
    -0.07
    åĬłå¼ºåŃ¦ä¹ł
    -0.07
    uess
    -0.07
     specifie
    -0.07
    MessageType
    -0.07
    meras
    -0.07
    éĽªçļĦ
    -0.06
    ega
    -0.06
    POSITIVE LOGITS
    jut
    0.08
    etic
    0.07
    zac
    0.07
     léo
    0.07
    ìķĪ
    0.07
    ÙĪج
    0.07
    ocken
    0.07
    odia
    0.07
    amore
    0.07
    ÑĦÑĤ
    0.07
    Activations Density 0.003%

    No Known Activations