© 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. 44932
    Prev
    Next
    INDEX
    Explanations

    direction, placement, and orientation

    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
    ÑĨин
    -0.09
    ÑĨина
    -0.07
    æĺ¯æĪij们
    -0.07
    gez
    -0.07
    вол
    -0.07
    å¿Ĺ
    -0.07
    accio
    -0.07
    è®°å½ķçļĦ
    -0.06
    oles
    -0.06
    ILES
    -0.06
    POSITIVE LOGITS
    缸åıįçļĦ
    0.09
    _direction
    0.09
    缸åıį
    0.09
    æĸ¹åIJij
    0.09
    Direction
    0.09
     Direction
    0.09
     direction
    0.09
    LTR
    0.08
    direction
    0.08
     reversal
    0.08
    Activations Density 0.040%

    No Known Activations