© 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. 10432
    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
    æķ´å¥Ĺ
    -0.08
    éĿ¢ç§¯çļĦ
    -0.08
    å®Įæķ´æĢ§
    -0.07
    éĩį
    -0.07
    éľĩ
    -0.07
    ç»ĵæŀĦçļĦ
    -0.07
     integrity
    -0.06
    issan
    -0.06
    æĢ»éĿ¢ç§¯
    -0.06
     Integrity
    -0.06
    POSITIVE LOGITS
     velocities
    0.12
     velocity
    0.10
    velocity
    0.10
     Velocity
    0.09
    çĽ¸å¯¹äºİ
    0.09
    Velocity
    0.09
    -relative
    0.09
     speeds
    0.09
    vel
    0.08
    æŶéĢŁ
    0.08
    Activations Density 0.004%

    No Known Activations