© 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. 41835
    Prev
    Next
    INDEX
    Explanations

    larger/smaller quantity

    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
     rust
    -0.07
     Dawn
    -0.06
    por
    -0.06
    ç¾İèªī
    -0.06
    bye
    -0.06
     er
    -0.06
    建议大家
    -0.06
    QU
    -0.05
     inline
    -0.05
     toile
    -0.05
    POSITIVE LOGITS
    åıįä¹ĭ
    0.09
    vice
    0.08
    缸åıį
    0.08
    stig
    0.08
     vice
    0.08
    ommel
    0.08
    downloads
    0.08
    iores
    0.08
    ä¸ĢéĹª
    0.08
    ramer
    0.08
    Activations Density 0.062%

    No Known Activations