© 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. 31780
    Prev
    Next
    INDEX
    Explanations

    pointing or facing directions

    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
    æݪæīĭ
    -0.09
    maal
    -0.08
    ogan
    -0.08
    สีมา
    -0.08
    धि
    -0.08
    isted
    -0.08
    htub
    -0.07
    mű
    -0.07
    uckle
    -0.07
    _OCCURRED
    -0.07
    POSITIVE LOGITS
    è¿ľæĸ¹
    0.09
     towards
    0.09
     toward
    0.09
    orial
    0.09
    çļĦæĸ¹åIJij
    0.08
    ÑģÑı
    0.08
    è¿ľæĸ¹çļĦ
    0.08
    antz
    0.07
    ä½ķæĸ¹
    0.07
    æĸ¹åIJijçļĦ
    0.07
    Activations Density 0.018%

    No Known Activations