© 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. 42432
    Prev
    Next
    INDEX
    Explanations

    dx/d, m/s, velocities

    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
    ieh
    -0.07
    ständ
    -0.06
    uable
    -0.06
    æĸ¹åľĨ
    -0.06
     Pelle
    -0.06
    iern
    -0.06
    èĢ³
    -0.06
    æ®ĭå¿į
    -0.06
    å½¢åĬ¿ä¸ĭ
    -0.06
    çł
    -0.06
    POSITIVE LOGITS
    ä¸Ģè·³
    0.08
    Normalized
    0.08
    pace
    0.08
     pace
    0.08
     velocities
    0.08
    åħ·ä½ĵæŶéĹ´
    0.07
    æŁı
    0.07
     slowed
    0.07
    åĪĨä¹ĭä¸Ģ
    0.07
    太快
    0.07
    Activations Density 0.001%

    No Known Activations