© 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. 8297
    Prev
    Next
    INDEX
    Explanations

    mountain names and features

    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
    åĪ°æľī
    -0.08
    æ·Į
    -0.07
     flow
    -0.07
    å¦Ĥæ°´
    -0.07
    液ä¸Ń
    -0.07
     drib
    -0.07
    çĤ¹æ»´
    -0.07
    νια
    -0.07
    液çļĦ
    -0.07
    èį¡æ¼¾
    -0.07
    POSITIVE LOGITS
    å·į峨
    0.12
    å±±èĦī
    0.11
     towering
    0.10
     mountains
    0.10
    èĢ¸
    0.10
    é«ĺèĢ¸
    0.09
     massif
    0.09
     гоÑĢÑĭ
    0.09
    æľĢé«ĺçĤ¹
    0.09
     formations
    0.09
    Activations Density 0.077%

    No Known Activations