© 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. 28273
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    regor
    -0.09
    èĩªçĦ¶èµĦæºIJåĴĮ
    -0.09
    ấn
    -0.09
    áb
    -0.08
    miny
    -0.08
    <|box_end|>
    -0.08
    æv
    -0.08
    èĩªå·±æĺ¯
    -0.08
    nds
    -0.08
    icina
    -0.08
    POSITIVE LOGITS
     Äijặn
    0.07
    al
    0.07
    ly
    0.07
    æĪĸéĥ¨åĪĨ
    0.07
     finer
    0.06
     οÏĢοί
    0.06
    ité
    0.06
    ä¼Ļ
    0.06
    å§Ķåijĺä¼ļå§Ķåijĺ
    0.06
    alp
    0.06
    Activations Density 0.000%

    No Known Activations