© 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. 27014
    Prev
    Next
    INDEX
    Explanations

    listing or telling about

    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
    Ỽt
    -0.10
    ipes
    -0.09
    æľīè¯Ŀ
    -0.08
    åħ¶ä»ĸçļĦ
    -0.07
    åIJİæľŁçļĦ
    -0.07
    ersen
    -0.07
    å¥ĩèīº
    -0.07
    orst
    -0.07
    çŃīåħ¶ä»ĸ
    -0.07
    ä¹Łå¾Īéĩįè¦ģ
    -0.07
    POSITIVE LOGITS
     firstly
    0.10
     NotImplementedError
    0.08
    å¿ĥéħ¸
    0.07
    对ä¸Ĭè¿°
    0.07
     systematically
    0.07
    ä¸Ĭè¿°
    0.07
     Ø£ÙĪÙĦاÙĭ
    0.07
     wÅĤaÅĽnie
    0.07
    å¦Ĥä¸Ĭ
    0.07
     comprehensive
    0.06
    Activations Density 0.003%

    No Known Activations