© 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. 1208
    Prev
    Next
    INDEX
    Explanations

    AC, SR, or ry followed by specific words

    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
    ä»Ģä¹Ī
    -0.07
    åľĪåľĪ
    -0.07
    gül
    -0.07
    алÑĮÑı
    -0.07
    äºĨä»Ģä¹Ī
    -0.07
    äger
    -0.07
    èģĶ
    -0.07
    ụi
    -0.06
    rito
    -0.06
    ":["
    -0.06
    POSITIVE LOGITS
    aisons
    0.08
    raphe
    0.08
    mith
    0.07
    Ĥ¬
    0.07
     Plast
    0.07
    ogramm
    0.07
    iley
    0.07
    unya
    0.07
    æĽ´çĶŁ
    0.07
    ัà¸Ļà¸ĺà¹Į
    0.07
    Activations Density 0.003%

    No Known Activations