© 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. 25638
    Prev
    Next
    INDEX
    Explanations

    speed and direction

    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
    çį¨
    -0.08
     লা
    -0.07
     runaway
    -0.07
    è¬
    -0.07
    é«ĺæķĪçļĦ
    -0.07
    cium
    -0.07
    æ¥ļæ¥ļ
    -0.07
    çĭ¬åįł
    -0.07
    çĭ¬
    -0.07
    onnement
    -0.07
    POSITIVE LOGITS
    sin
    0.09
     sin
    0.09
     directional
    0.09
    cos
    0.09
     sine
    0.08
     sinus
    0.08
    (cos
    0.08
    并æĮīçħ§
    0.07
     Sin
    0.07
    andong
    0.07
    Activations Density 0.023%

    No Known Activations