© 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. 44906
    Prev
    Next
    INDEX
    Explanations

    First, broader, battle, test, immun, twisted

    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
    æĪĸå°ij
    -0.08
    ì§ľ
    -0.07
    ä¸įè¿ĩäºĨ
    -0.07
    ?p
    -0.07
    ä¸Ģ读
    -0.07
    ãģĹãĤį
    -0.06
    ç½Ĺ纳
    -0.06
    istos
    -0.06
    astos
    -0.06
    åı¯æŁ¥çľĭ
    -0.06
    POSITIVE LOGITS
    æĹłè®ºä»İ
    0.09
    æĹłè®º
    0.08
    æĮij
    0.07
    å«
    0.07
    entin
    0.07
     mojo
    0.07
    .sf
    0.07
    æĹłè®ºå¦Ĥä½ķ
    0.07
    нк
    0.06
    ä»İ严
    0.06
    Activations Density 0.001%

    No Known Activations