© 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. 33005
    Prev
    Next
    INDEX
    Explanations

    negation or unsuitability

    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
    à§ģষ
    -0.09
    ivet
    -0.08
    estruc
    -0.08
    çļĦè¿Ļä¸Ģ
    -0.08
    imme
    -0.08
    KeyEvent
    -0.08
    家æķĻ
    -0.08
    åĪ·åĪ·
    -0.08
    acor
    -0.08
    çIJĨ论çłĶ究
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įåı¯èĥ½
    0.08
    èĶ¼
    0.07
    ere
    0.06
    åĽłä¸ºåıªæľī
    0.06
    ибо
    0.06
    aso
    0.06
    iner
    0.06
    o
    0.06
    asy
    0.06
    ç»®
    0.05
    Activations Density 0.014%

    No Known Activations