© 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. 33919
    Prev
    Next
    INDEX
    Explanations

    UI elements and controls

    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
    ützt
    -0.07
    -0.07
    jsonp
    -0.06
    ÙĦاع
    -0.06
     and
    -0.06
    /topics
    -0.06
    acro
    -0.06
    åħ±è¿Ľ
    -0.06
    /Runtime
    -0.06
    POSITIVE LOGITS
    isle
    0.08
    aked
    0.08
    fid
    0.08
    æıIJä¾Ľä»»ä½ķ
    0.07
    éľĢè¦ģæıIJåīį
    0.07
    sf
    0.07
    TargetException
    0.07
    两åѦä¸Ģåģļ
    0.07
    cid
    0.07
    د
    0.07
    Activations Density 0.019%

    No Known Activations