© 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. 9633
    Prev
    Next
    INDEX
    Explanations

    reading

    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
    å¦į
    -0.08
    æĸĭ
    -0.07
    èĤĩ
    -0.07
    è¦ģè¾¾åĪ°
    -0.07
    mdl
    -0.07
    psz
    -0.07
    rš
    -0.07
    é½
    -0.07
    -tool
    -0.07
    çļĦéĢļçŁ¥
    -0.07
    POSITIVE LOGITS
    venta
    0.07
    è´¹
    0.07
    idden
    0.07
    è´¹çļĦ
    0.07
    éIJĺ
    0.07
    oteles
    0.07
    olist
    0.07
    ned
    0.06
    anea
    0.06
    ׾×ķת
    0.06
    Activations Density 0.007%

    No Known Activations