© 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. 32638
    Prev
    Next
    INDEX
    Explanations

    standard input/output streams

    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
    orgia
    -0.08
    kho
    -0.08
    kking
    -0.08
    systems
    -0.08
    å¾ħåľ¨
    -0.08
    åijĨåľ¨
    -0.07
    zza
    -0.07
    èİŀ
    -0.07
    ierzch
    -0.07
    MBER
    -0.07
    POSITIVE LOGITS
     input
    0.07
    æĪĸåħ¶ä»ĸ
    0.07
    å¾Īæĸ¹ä¾¿
    0.06
    å¸ĥ伦
    0.06
    æĪĸçĶ±
    0.06
    沦
    0.06
    ople
    0.06
    æĪĸéĢļè¿ĩ
    0.06
     Hancock
    0.06
    /console
    0.06
    Activations Density 0.120%

    No Known Activations