© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26921
    Prev
    Next
    INDEX
    Explanations

    method signature

    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
    راÙĨ
    -0.07
     merch
    -0.07
    niest
    -0.07
    åħ¨åı°
    -0.07
    åĨ³
    -0.07
    alez
    -0.07
    eschi
    -0.07
     Kooper
    -0.07
    log
    -0.07
    è¨Ģä¹ĭ
    -0.07
    POSITIVE LOGITS
    Ïĥκε
    0.07
    orro
    0.07
    usel
    0.07
    èĭ¥å¹²æĦıè§ģ
    0.07
     bevorzug
    0.07
    полÑĥ
    0.07
    车系
    0.07
    -negative
    0.07
    asuk
    0.06
    ArrayType
    0.06
    Activations Density 0.001%

    No Known Activations