© 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. 11245
    Prev
    Next
    INDEX
    Explanations

    AS BEGIN

    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
     edital
    -0.07
    .ibm
    -0.07
     jMenuItem
    -0.07
    chio
    -0.07
    tev
    -0.07
    ีà¸ģ
    -0.07
    esp
    -0.07
    ajian
    -0.07
    indh
    -0.07
    æŃĩå°Ķ
    -0.07
    POSITIVE LOGITS
    UserProfile
    0.07
    人åķĬ
    0.06
    Nx
    0.06
    rne
    0.06
    HING
    0.06
    çļĦç¡®æĺ¯
    0.06
    èĤ¡ä¸ľåıĬ
    0.06
    elsen
    0.06
    oons
    0.06
     strive
    0.06
    Activations Density 0.018%

    No Known Activations