© 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. 3088
    Prev
    Next
    INDEX
    Explanations

    automation starts

    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
    áĢŃáĢ¯áĢ·
    -0.08
    åĵŃ声
    -0.08
    اء
    -0.07
    REAM
    -0.07
    æľīäºĭ
    -0.07
    à¸Ķ
    -0.07
    æĪij们åħĪ
    -0.07
    YNAMIC
    -0.07
    egl
    -0.06
    -scripts
    -0.06
    POSITIVE LOGITS
    纪
    0.07
    quem
    0.07
     ::
    0.07
    åħ¥å¸Ĥ
    0.07
    èµ°è¿ĩäºĨ
    0.06
    title
    0.06
     lege
    0.06
    åĨĢ
    0.06
    åºĶæľīçļĦ
    0.06
    @m
    0.06
    Activations Density 0.006%

    No Known Activations