© 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. 26531
    Prev
    Next
    INDEX
    Explanations

    angles and shapes

    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
    åĿĩè¡¡
    -0.08
    å§ĭç¥ĸ
    -0.07
    æ·Ĩ
    -0.07
    æľīæīĢæĢĿ
    -0.07
    æĶ«
    -0.07
    漪
    -0.07
    ocie
    -0.07
     Svens
    -0.07
    äºĶèī²
    -0.06
    æĽ³
    -0.06
    POSITIVE LOGITS
    çĭŃ
    0.09
    æ°¸ä¹ħæĢ§
    0.09
    æ°¸ä¹ħ
    0.09
    å½¢æĪIJäºĨä¸Ģ个
    0.08
    -angle
    0.08
    angled
    0.08
    åį§é¾Ļ
    0.08
    æĹłéĻIJ
    0.08
    angling
    0.08
    omed
    0.08
    Activations Density 0.003%

    No Known Activations