© 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. 12479
    Prev
    Next
    INDEX
    Explanations

    There are

    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
    ness
    -0.13
    Ø©
    -0.12
    ation
    -0.10
    ulate
    -0.10
    ature
    -0.09
    RARY
    -0.09
    tedir
    -0.08
    Äĥturi
    -0.08
    ÃŃnu
    -0.08
    éĺħè¯»æľ¬æĸĩ
    -0.08
    POSITIVE LOGITS
    abouts
    0.10
    ers
    0.09
    'll
    0.09
    en
    0.08
    ãģĺãĤģãģ¦
    0.08
    upon
    0.08
    an
    0.08
    on
    0.08
    ики
    0.08
    м
    0.07
    Activations Density 0.139%

    No Known Activations