© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27106
    Prev
    Next
    INDEX
    Explanations

    pro followed by quest, gress, vid, tection

    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
    iculty
    -0.08
    -0.08
    stile
    -0.08
    dade
    -0.08
    ÑģÑĤоÑĩ
    -0.08
    tima
    -0.08
    czeÅĽ
    -0.07
    аниÑı
    -0.07
    ÑģÑĤÑĢо
    -0.07
    ãģªãģĮãĤī
    -0.07
    POSITIVE LOGITS
    crast
    0.10
    yecto
    0.09
    xima
    0.09
    xies
    0.09
    olet
    0.09
    ximity
    0.09
    er
    0.09
    vincial
    0.09
    essor
    0.09
    ives
    0.09
    Activations Density 0.155%

    No Known Activations