© 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. 32821
    Prev
    Next
    INDEX
    Explanations

    special characters, punctuation, or code formatting

    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
    顧
    -0.06
    顾
    -0.06
    çĭ¬èĩª
    -0.06
    IOS
    -0.06
     _$
    -0.06
    åģ¿
    -0.06
    工贸
    -0.06
    åĽŃçļĦ
    -0.06
    ç¼Ģ
    -0.06
    alin
    -0.06
    POSITIVE LOGITS
    çĽ¸ä¿¡æĪij
    0.08
    endra
    0.08
    )':
    0.08
    )":
    0.07
    对åħ¶è¿Ľè¡Į
    0.07
    rary
    0.07
    æĥ³åĩº
    0.07
    æѦ
    0.07
     eds
    0.07
     {}:
    0.07
    Activations Density 0.017%

    No Known Activations