© 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. 58481
    Prev
    Next
    INDEX
    Explanations

    programming code examples

    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
    رد
    -0.07
    koľ
    -0.07
    ãģĵãĤį
    -0.07
     Aussch
    -0.07
    amay
    -0.07
    macros
    -0.07
     Anf
    -0.06
    ched
    -0.06
     غاÙĦ
    -0.06
     Seben
    -0.06
    POSITIVE LOGITS
    æħ·
    0.07
    iba
    0.07
    arz
    0.07
    ilu
    0.07
    使çĶ¨åIJİ
    0.06
    ego
    0.06
    干干åĩĢåĩĢ
    0.06
    örn
    0.06
    oppable
    0.06
    åıªæľīè¿Ļæł·
    0.06
    Activations Density 0.002%

    No Known Activations