© 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. 41205
    Prev
    Next
    INDEX
    Explanations

    For references

    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
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    åĪ©æµ¦
    -0.07
    azu
    -0.07
    ÑĥÑģÑĤ
    -0.06
    å±ĭ
    -0.06
    俨
    -0.06
    åĨ¤
    -0.06
    .Promise
    -0.06
    åħ¬ä¼Ĺå¹³åı°
    -0.06
    azy
    -0.06
    POSITIVE LOGITS
    éĤ£äºĽäºº
    0.08
    uwe
    0.08
    egas
    0.08
    æĪij们æĿ¥
    0.07
     Mots
    0.07
    fie
    0.07
    iversity
    0.07
    Featured
    0.07
    æľīè¿Ļæł·çļĦ
    0.07
    Occurred
    0.07
    Activations Density 0.002%

    No Known Activations