© 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. 1327
    Prev
    Next
    INDEX
    Explanations

    extract column or links

    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
    oland
    -0.08
    ë°ĸìĹIJ
    -0.08
    _SWAP
    -0.08
    owod
    -0.07
    ãĥ³ãĥĹ
    -0.07
    odb
    -0.07
    rolet
    -0.07
    å¹´åĽ½å®¶
    -0.07
    orz
    -0.07
    è§ģéĿ¢ä¼ļ
    -0.07
    POSITIVE LOGITS
    utton
    0.07
    éŃĦ
    0.06
    ymous
    0.06
    ลà¸Ńย
    0.06
    .preference
    0.06
     îns
    0.06
    ìĪĻ
    0.06
    `()
    0.06
    ä¸įæĶ¾å¼ĥ
    0.06
     multiplic
    0.06
    Activations Density 0.001%

    No Known Activations