© 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. 12935
    Prev
    Next
    INDEX
    Explanations

    names ending in ica

    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
    enea
    -0.08
    éĥ¨åĪĨåĨħ容
    -0.08
    <|repo_name|>
    -0.08
    ostro
    -0.08
    plat
    -0.08
    åįĬæŃ¥
    -0.08
    prit
    -0.07
    好æĸĩ
    -0.07
    uest
    -0.07
    æłij人
    -0.07
    POSITIVE LOGITS
    çĬ¹
    0.07
     dec
    0.06
    å·¥ä¸ļçĶŁäº§
    0.06
    elts
    0.06
     tr
    0.06
     see
    0.06
     wire
    0.06
    éī´
    0.06
     q
    0.06
     until
    0.06
    Activations Density 0.138%

    No Known Activations