© 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. 44962
    Prev
    Next
    INDEX
    Explanations

    points, junctions, branches

    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
     subrange
    -0.08
    λαν
    -0.07
    忱
    -0.07
    åIJ´æ±Ł
    -0.07
     PROGMEM
    -0.07
    è¶Ł
    -0.07
    ãng
    -0.07
    eits
    -0.07
    _lengths
    -0.07
    èī²å·®
    -0.07
    POSITIVE LOGITS
    èĬĤçĤ¹
    0.10
     node
    0.09
    æŀ¢çº½
    0.09
    èĬĤçĤ¹çļĦ
    0.09
    ç»ĵçĤ¹
    0.09
    node
    0.09
    å¤ĦåĪĨ
    0.09
     junction
    0.08
     hub
    0.08
    èģļ
    0.08
    Activations Density 0.022%

    No Known Activations