© 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. 9852
    Prev
    Next
    INDEX
    Explanations

    volume overload decrease

    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
     tightening
    -0.11
     tightly
    -0.11
     tighter
    -0.10
     tight
    -0.10
     Tight
    -0.10
    éĹŃ
    -0.09
     tightened
    -0.09
    æĭ§ç´§
    -0.09
    åļ´
    -0.09
     compact
    -0.09
    POSITIVE LOGITS
     openness
    0.14
    å¼ĢæĶ¾æĢ§
    0.14
     freely
    0.14
    èĩªçĶ±
    0.14
    èĩªçĶ±çļĦ
    0.14
     freedom
    0.13
    å¼ĢæĶ¾
    0.13
     Ñģвобо
    0.13
    çļĦèĩªçĶ±
    0.13
     freedoms
    0.13
    Activations Density 0.884%

    No Known Activations