© 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. 61486
    Prev
    Next
    INDEX
    Explanations

    sqrt calculation

    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
    osc
    -0.08
    åĪĨ享åĪ°æľĭåıĭåľĪ
    -0.07
    ehr
    -0.07
    iller
    -0.07
    तर
    -0.07
    escu
    -0.07
    igné
    -0.07
    stag
    -0.07
    è¾Ľéħ¸
    -0.07
    æĿ
    -0.06
    POSITIVE LOGITS
    Radius
    0.08
     Radius
    0.08
    æľĪåľĨ
    0.07
    åįĬå¾Ħ
    0.07
    дÑĥк
    0.07
    radius
    0.07
    athering
    0.07
    顾åIJįæĢĿ
    0.07
    longitude
    0.07
    æĹłå°ĺ
    0.07
    Activations Density 0.005%

    No Known Activations