© 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. 26005
    Prev
    Next
    INDEX
    Explanations

    directional or positional prefixes

    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
    ercial
    -0.07
    ×ł×¡
    -0.07
    æīĢéķ¿
    -0.06
    èĥĮéĿł
    -0.06
    unge
    -0.06
    æīij
    -0.06
    ÑĢовок
    -0.06
    ATUS
    -0.06
    thesis
    -0.06
    çŃ¾æĶ¶
    -0.06
    POSITIVE LOGITS
    zan
    0.08
    èĮ¹
    0.07
     Hampton
    0.07
    uite
    0.07
    ä¸įè°ĥ
    0.07
    olid
    0.07
     Diri
    0.07
    esub
    0.07
    ulta
    0.07
    _RET
    0.06
    Activations Density 0.095%

    No Known Activations