© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62840
    Prev
    Next
    INDEX
    Explanations

    markdown headings or bold text

    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
    edal
    -0.07
    atty
    -0.07
    çĶ¸
    -0.07
    第ä¸Ģ代
    -0.07
    Ãło
    -0.07
    dao
    -0.07
    ||(
    -0.07
    åŃĹ第
    -0.07
    finity
    -0.07
    ouce
    -0.07
    POSITIVE LOGITS
    æµ´
    0.07
    SRC
    0.06
    ä»Ĭ
    0.06
     addButton
    0.06
    endum
    0.06
    ä¸Ńå°ıåŀĭ
    0.06
    ä¸į失
    0.06
    gab
    0.06
    schlag
    0.06
     offending
    0.06
    Activations Density 0.001%

    No Known Activations