© 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. 18651
    Prev
    Next
    INDEX
    Explanations

    `pd`, `al`, `h`

    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
    /
    -0.07
    ä¸ĭåIJĮ
    -0.06
    èĢĮæĹłæ³ķ
    -0.06
    vek
    -0.06
     repro
    -0.06
    ict
    -0.06
     Szer
    -0.06
    λÏī
    -0.06
    å¦Ĥæŀľåıijçİ°
    -0.06
     fot
    -0.06
    POSITIVE LOGITS
    acho
    0.08
    åıĪå¦Ĥ
    0.07
    éĺħè¯»æľ¬æĸĩåīį
    0.07
    ocache
    0.07
    _vlog
    0.07
    ustin
    0.07
    OfFile
    0.07
    uger
    0.07
    åıĪåĪ°äºĨ
    0.07
    ãģ¾ãģļ
    0.07
    Activations Density 0.002%

    No Known Activations