© 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. 13873
    Prev
    Next
    INDEX
    Explanations

    able to be approximated

    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
    udes
    -0.07
    éļĪ
    -0.07
     undert
    -0.07
    çľ¼çķĮ
    -0.07
    idth
    -0.07
    oÅĽci
    -0.07
    astic
    -0.07
    éĸĭæĶ¾
    -0.07
    éĮ¯
    -0.07
    ofs
    -0.07
    POSITIVE LOGITS
     easily
    0.11
    izable
    0.10
    isable
    0.10
    able
    0.09
     بسÙĩÙĪÙĦØ©
    0.09
    nable
    0.09
     feas
    0.09
     comfortably
    0.09
    atable
    0.08
     fácilmente
    0.08
    Activations Density 0.049%

    No Known Activations