© 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. 48734
    Prev
    Next
    INDEX
    Explanations

    biological context and characteristics

    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
    ìŁģ
    -0.09
    abouts
    -0.08
    Ñģловно
    -0.08
    ataires
    -0.08
    oes
    -0.07
    naires
    -0.07
    Ñģион
    -0.07
    ENCY
    -0.07
    ingly
    -0.07
    ETERS
    -0.07
    POSITIVE LOGITS
    istic
    0.09
    åŃ¦å®¶
    0.09
    -human
    0.09
    ìį¨
    0.08
    organic
    0.08
    yak
    0.08
    ility
    0.07
    ically
    0.07
    èĤ¡
    0.07
    éĻªå®¡åijĺ
    0.07
    Activations Density 0.073%

    No Known Activations