© 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. 15954
    Prev
    Next
    INDEX
    Explanations

    angles and rotations

    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
    æľ«
    -0.08
    æľ«æľŁ
    -0.07
    ropolis
    -0.07
    atina
    -0.07
    .lb
    -0.07
    Singleton
    -0.07
    ä¸įæ²»
    -0.07
    ijnen
    -0.07
     vit
    -0.07
    éģĤ
    -0.07
    POSITIVE LOGITS
     compass
    0.09
    æĹĭ转
    0.08
     clockwise
    0.08
    ä»İ天
    0.07
     rotational
    0.07
    oris
    0.07
    achel
    0.07
    ally
    0.07
    compass
    0.07
     sin
    0.07
    Activations Density 0.001%

    No Known Activations