© 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. 60852
    Prev
    Next
    INDEX
    Explanations

    boundary, end, control, avenue, bottom

    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
    ioc
    -0.07
    æľ¬æĸĩçĶ±
    -0.07
    ÑĨеп
    -0.07
     Antw
    -0.06
    cairo
    -0.06
    iju
    -0.06
    åĽºæĢģ
    -0.06
    åľĪçļĦ
    -0.06
    apes
    -0.06
    rut
    -0.06
    POSITIVE LOGITS
    entes
    0.08
    éĺĸ
    0.07
    rophe
    0.07
    ences
    0.07
    boundary
    0.07
    è¦ģåĬłå¼º
    0.07
     conv
    0.07
    irt
    0.07
     Curtain
    0.07
    alam
    0.06
    Activations Density 0.003%

    No Known Activations