© 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. 20148
    Prev
    Next
    INDEX
    Explanations

    byline attribution

    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
     âĢ¦
    -0.07
    âĢ¦âĢ¦
    -0.07
    Âł
    -0.07
    âĢ¦
    -0.06
    ↵↵
    -0.06
    ueva
    -0.06
    âĢ¦.
    -0.06
    沧æ¡ij
    -0.06
    èIJ¥
    -0.06
     âĢ¦.
    -0.06
    POSITIVE LOGITS
    ä¸ĭä¸Ģç¯ĩ
    0.08
    åħ¶æŀĹ
    0.08
     Deal
    0.08
     getr
    0.08
    ç·Ĵ
    0.08
     fata
    0.08
    çŃīçĿĢä½ł
    0.08
     tslib
    0.08
    ventus
    0.08
    alion
    0.08
    Activations Density 0.067%

    No Known Activations