© 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. 56273
    Prev
    Next
    INDEX
    Explanations

    develop and translate

    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
    /********
    -0.07
    arate
    -0.07
    éron
    -0.07
     Hatch
    -0.07
    اÙĤ
    -0.07
    acap
    -0.07
    aura
    -0.07
    _STORAGE
    -0.07
    '](
    -0.07
    ÙĪÙħاÙĨ
    -0.07
    POSITIVE LOGITS
    并ç»ı
    0.17
    å¹¶è¿Ľè¡Į
    0.15
    并éĢļè¿ĩ
    0.14
    并对åħ¶
    0.13
    并确ä¿Ŀ
    0.13
    并çĶ¨
    0.13
    并çĶ±
    0.13
    并就
    0.12
    并åģļ好
    0.12
    åIJİç»ı
    0.12
    Activations Density 0.460%

    No Known Activations