© 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. 43372
    Prev
    Next
    INDEX
    Explanations

    math expressions and code path

    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
    åĶ¯çĭ¬
    -0.07
    weit
    -0.07
    uccio
    -0.06
     aba
    -0.06
    kw
    -0.06
    æĥ°
    -0.06
     *(*
    -0.06
     Trustees
    -0.06
    опо
    -0.06
    cion
    -0.06
    POSITIVE LOGITS
    NJ
    0.08
    cona
    0.08
     SND
    0.07
    ãģ¨ãģĦãģ£ãģ¦
    0.07
    bst
    0.07
    eward
    0.07
    laut
    0.07
    faz
    0.07
    åĽĽæµ·
    0.07
    isst
    0.07
    Activations Density 0.001%

    No Known Activations