© 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. 13595
    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
     Istitu
    -0.10
     deteri
    -0.10
     ÐĴÑģÑĤÑĢе
    -0.09
    ingroup
    -0.09
     ÐĴедÑĥ
    -0.09
     ÐŁÑĢедÑģÑĤави
    -0.09
     Postar
    -0.09
     ÐŁÐ¾Ð¿ÑĢо
    -0.09
     Attra
    -0.09
     Сооб
    -0.09
    POSITIVE LOGITS
    0.11
    Âł
    0.07
    7
    0.06
     **
    0.06
    0
    0.06
    1
    0.06
    -
    0.06
    "
    0.06
    åĶ¯çĭ¬
    0.06
    c
    0.05
    Activations Density 0.505%

    No Known Activations

    This feature has no known activations.