© 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. 15654
    Prev
    Next
    INDEX
    Explanations

    local variables

    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
    å½Ĵ
    -0.08
    æѸ
    -0.07
    imore
    -0.07
    åħļæĶ¿æľºåħ³
    -0.07
    èĢĮå½Ĵ
    -0.06
    æĿİå®ģ
    -0.06
    lest
    -0.06
    便çķ¶
    -0.06
    urin
    -0.06
    ä¸įåºĶæ±Ĥ
    -0.06
    POSITIVE LOGITS
    å½ĵåľ°çļĦ
    0.10
     local
    0.10
    æľ¬åľ°
    0.09
    å½ĵåľ°
    0.08
     Local
    0.08
    å±Ģéĥ¨
    0.08
    local
    0.08
     лока
    0.08
    hte
    0.08
    -local
    0.08
    Activations Density 0.101%

    No Known Activations