© 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. 17922
    Prev
    Next
    INDEX
    Explanations

    movement towards or away

    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
    å¾Ĺèµ·
    -0.08
    æĹĹé¼ĵ
    -0.07
    tric
    -0.07
    沿çĶ¨
    -0.07
    æĥĬ天
    -0.07
    amus
    -0.07
    éģŀ
    -0.07
    éĩij鸡
    -0.07
    éĢĴ
    -0.07
    eson
    -0.07
    POSITIVE LOGITS
     towards
    0.12
    è¶ĭåIJij
    0.12
     toward
    0.11
    åIJijçĿĢ
    0.09
    æľĿçĿĢ
    0.09
     Towards
    0.09
    éĿłæĭ¢
    0.08
    Towards
    0.08
    è¶ĭ
    0.08
     ÑģÑĤÑĢемиÑĤÑģÑı
    0.08
    Activations Density 0.020%

    No Known Activations