© 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. 49473
    Prev
    Next
    INDEX
    Explanations

    end of

    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
    ়
    -0.10
    -eslint
    -0.09
    itous
    -0.09
    raries
    -0.08
    anguard
    -0.08
     Setia
    -0.08
    ลำà¸Ķัà¸ļ
    -0.08
    adop
    -0.08
    éĩĮæĺĤ
    -0.08
    izontal
    -0.08
    POSITIVE LOGITS
    owment
    0.12
    urance
    0.12
    angered
    0.12
    most
    0.11
    sWith
    0.10
    ocrin
    0.10
    ogenous
    0.10
    ocrine
    0.10
    ividual
    0.09
    lessly
    0.09
    Activations Density 0.116%

    No Known Activations