© 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. 45732
    Prev
    Next
    INDEX
    Explanations

    connect wires

    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
    èĩªè§ī
    -0.06
    裾
    -0.06
     champ
    -0.06
    两人çļĦ
    -0.06
     optimum
    -0.06
    亲身
    -0.06
    ä¸¤äººåľ¨
    -0.06
    nev
    -0.06
     matur
    -0.06
    éĢIJ
    -0.06
    POSITIVE LOGITS
    å®ŀä½ĵ
    0.09
    TextNode
    0.09
    abstract
    0.09
    ationToken
    0.08
     dihub
    0.08
     abstraction
    0.08
    -connect
    0.08
    æ·¡æ·¡
    0.08
     connect
    0.08
    實é«Ķ
    0.08
    Activations Density 0.015%

    No Known Activations