© 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. 65470
    Prev
    Next
    INDEX
    Explanations

    cut off or cut out words

    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
    zinho
    -0.09
    champ
    -0.07
    heur
    -0.07
    aging
    -0.07
    füg
    -0.07
    åħ¶éģĵ
    -0.07
    ardo
    -0.06
    hawk
    -0.06
    кÑĥл
    -0.06
    åı¯æĥ³
    -0.06
    POSITIVE LOGITS
    ropolitan
    0.09
    neider
    0.09
    warz
    0.09
    ergestellt
    0.09
    ters
    0.08
     á»ĵn
    0.08
    ãĥ³ãĤ°
    0.08
    ories
    0.08
    尼迪
    0.08
    umbs
    0.08
    Activations Density 0.001%

    No Known Activations