© 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. 25829
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    ÙĬÙĨ
    -0.07
    ycin
    -0.07
    igare
    -0.06
    Äįka
    -0.06
    .IN
    -0.06
    çŤ
    -0.06
    AN
    -0.06
    âĢ¦
    -0.06
    iali
    -0.06
    illot
    -0.06
    POSITIVE LOGITS
    κη
    0.08
    terra
    0.08
    imte
    0.08
    otime
    0.08
    ãģłãģijãģ§ãĤĤ
    0.08
    oard
    0.07
    à¸ģรรม
    0.07
    OUNTER
    0.07
    ffel
    0.07
    ält
    0.07
    Activations Density 0.001%

    No Known Activations