© 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. 48842
    Prev
    Next
    INDEX
    Explanations

    space between or clearance

    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
    åħ·æľīè¾ĥ强çļĦ
    -0.08
    ocos
    -0.08
    mixed
    -0.07
    åħ·æľīå¾Ī强çļĦ
    -0.07
     mixed
    -0.07
     overwhelmingly
    -0.07
    uat
    -0.07
     divisive
    -0.07
     ÑģилÑĮнÑĭе
    -0.07
    ümü
    -0.07
    POSITIVE LOGITS
     distance
    0.11
    è·Ŀ离
    0.10
    çļĦè·Ŀ离
    0.10
     distances
    0.10
    è·ĿéĽ¢
    0.10
    è·Ŀ
    0.10
    distance
    0.09
     sufficient
    0.09
     separation
    0.09
     spacing
    0.09
    Activations Density 0.020%

    No Known Activations