© 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. 20186
    Prev
    Next
    INDEX
    Explanations

    let, what is, for example

    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
    asiun
    -0.08
    handleRequest
    -0.08
    anmar
    -0.08
    razi
    -0.08
    ujan
    -0.08
    ä»ħ代表
    -0.08
     espirit
    -0.07
    å¤Ħå¤Ħ
    -0.07
    usher
    -0.07
    volv
    -0.07
    POSITIVE LOGITS
    åħ¶ä»ĸ
    0.07
    èĢĥèĻij
    0.07
    çľĭ
    0.06
    os
    0.06
    ESP
    0.06
     nô
    0.06
    åĺ´
    0.06
    çĦ¶èĢĮ
    0.06
    ...*
    0.06
    å¾Ħ
    0.06
    Activations Density 0.577%

    No Known Activations