© 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. 23949
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    å¸ĮæľĽå¯¹æĤ¨
    -0.07
    åıĬåºĶçĶ¨
    -0.07
    åIJ¦
    -0.07
    _THROW
    -0.06
    alts
    -0.06
    çħ½
    -0.06
    åħĭæŀĹ
    -0.06
    ç«ĭå¾·
    -0.06
    _LOOK
    -0.06
    åıĬåħ¶å®ĥ
    -0.06
    POSITIVE LOGITS
    uxt
    0.09
    ä¸įåĪ°çļĦ
    0.08
    ä¸Ģè¿Ľ
    0.07
    ä¸įåĪ°äºĨ
    0.07
    两åı£
    0.07
    åī©
    0.07
    رÙĪÙĨ
    0.07
    æ§Ľ
    0.07
     Ñĥв
    0.07
    masked
    0.07
    Activations Density 0.003%

    No Known Activations