© 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. 32283
    Prev
    Next
    INDEX
    Explanations

    speed and velocity

    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
    建çŃijç»ĵæŀĦ
    -0.08
    å¿łå®ŀ
    -0.06
     structural
    -0.06
    åĨħ容ä¸İ
    -0.06
     sar
    -0.06
    éļıçĿĢå¹´é¾Ħ
    -0.06
     itself
    -0.06
     source
    -0.06
    ç»ĵæŀĦä¸İ
    -0.06
    enskap
    -0.06
    POSITIVE LOGITS
    aup
    0.09
     اصط
    0.09
    elin
    0.08
     newPos
    0.08
    æĴŀ
    0.08
     velocities
    0.08
    _prediction
    0.08
    ä½łä»¬éĥ½
    0.08
     Ùħص
    0.07
    ëł¹
    0.07
    Activations Density 0.001%

    No Known Activations