© 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. 4265
    Prev
    Next
    INDEX
    Explanations

    list/array syntax

    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
    <decltype
    -0.08
    <typeof
    -0.07
    ersist
    -0.07
    æĴµ
    -0.07
    __(*
    -0.06
     Toda
    -0.06
    æĤ´
    -0.06
    paren
    -0.06
    @m
    -0.06
     âĵĴ
    -0.06
    POSITIVE LOGITS
    tene
    0.07
    zez
    0.07
    åįķä½įåıĤåĬł
    0.07
    禮
    0.07
    ORN
    0.07
    èı
    0.07
     saline
    0.07
    ç£IJ
    0.06
    é¦Ĩ
    0.06
    orns
    0.06
    Activations Density 0.012%

    No Known Activations