© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 43162
    Prev
    Next
    INDEX
    Explanations

    like so: or like this:

    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
    /
    -0.06
    å°ıåŃIJ
    -0.06
    ernal
    -0.06
    **”
    -0.06
    带
    -0.06
     enda
    -0.06
    1
    -0.06
    orm
    -0.06
     e
    -0.06
    æ¯Ķå¦Ĥåľ¨
    -0.05
    POSITIVE LOGITS
    :
    0.11
    ï¼ļ
    0.10
    _:
    0.10
    以ä¸ĭãģ®
    0.09
    :^
    0.09
    +:
    0.09
    !:
    0.09
    .:
    0.09
    ï¼ļ</
    0.08
    :.
    0.08
    Activations Density 0.088%

    No Known Activations