© 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. 29989
    Prev
    Next
    INDEX
    Explanations

    word count and limits

    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
    ptype
    -0.07
    æĢ§éĹ®é¢ĺ
    -0.07
    alsy
    -0.07
    å½ĵäºĭ
    -0.07
     Pew
    -0.07
     Fortune
    -0.06
    yp
    -0.06
    acle
    -0.06
    .parts
    -0.06
    åĬ«
    -0.06
    POSITIVE LOGITS
     paragraphs
    0.08
    ÑĭÑĢ
    0.08
    ková
    0.07
    Ñĩо
    0.07
    管çIJĨä¸Ńå¿ĥ
    0.07
    kou
    0.07
    以ä¸ĬçļĦ
    0.07
    czyn
    0.07
    enes
    0.07
    uib
    0.07
    Activations Density 0.008%

    No Known Activations