© 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. 15809
    Prev
    Next
    INDEX
    Explanations

    efficacious, ridicule, indecent, off base, modest, chopped

    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
    otre
    -0.08
    vera
    -0.08
    upas
    -0.07
    anke
    -0.07
    agua
    -0.07
    eku
    -0.07
    ìm
    -0.07
    ikir
    -0.07
    اة
    -0.07
    elib
    -0.07
    POSITIVE LOGITS
    ness
    0.11
     enough
    0.08
    ç¨ĭ度
    0.08
    形容
    0.08
    çļĦç¨ĭ度
    0.08
    liness
    0.08
    主è¦ģ表çİ°åľ¨
    0.08
    -bodied
    0.08
    çĶļèĩ³æľīäºĽ
    0.07
    ãģĭãģ¤
    0.07
    Activations Density 0.017%

    No Known Activations