© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48504
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or periods

    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
    possible
    -0.07
    -0.07
    ESCO
    -0.07
     âĢ¦
    -0.07
     âĢİ
    -0.06
    常
    -0.06
    anho
    -0.06
    anju
    -0.06
    nofollow
    -0.06
     bref
    -0.06
    POSITIVE LOGITS
    sdk
    0.08
    ť
    0.07
    enton
    0.07
    enaar
    0.07
    åıijåijĨ
    0.07
    sst
    0.07
    Ø©
    0.07
    åį³çĶ¨
    0.07
    çĺª
    0.07
    çģ¿çģ¿
    0.06
    Activations Density 0.001%

    No Known Activations