© 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. 13608
    Prev
    Next
    INDEX
    Explanations

    job descriptions, instructions, and descriptions

    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
    以ä¸ĭåĩłçĤ¹
    -0.08
     appunto
    -0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    -0.08
    bidden
    -0.07
    phans
    -0.07
    äºĨ解ä¸Ģä¸ĭåIJ§
    -0.07
    mittag
    -0.07
     theirs
    -0.07
    viously
    -0.07
    {}'.
    -0.07
    POSITIVE LOGITS
    orem
    0.11
    oretical
    0.10
    !!:
    0.09
     inoltre
    0.09
     therefore
    0.09
    !!!!!!!!
    0.09
     tehát
    0.08
    åĽłæѤ
    0.08
    oret
    0.08
     importantly
    0.08
    Activations Density 0.115%

    No Known Activations