© 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. 23529
    Prev
    Next
    INDEX
    Explanations

    prior Art

    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
    oces
    -0.07
    ãģĺãĤģ
    -0.07
    ances
    -0.07
    æĢ§ä»¥åıĬ
    -0.07
    ãģĺãĤģãģ¦
    -0.07
     Prof
    -0.06
    ([('
    -0.06
    èĢĮåĿIJ
    -0.06
    ä¼ļåıijçĶŁ
    -0.06
    гово
    -0.06
    POSITIVE LOGITS
     either
    0.08
    aven
    0.07
    è¦ģä¹Ī
    0.07
    ISA
    0.07
    isoft
    0.07
    plement
    0.07
    è¦ģä¹Īæĺ¯
    0.07
    strap
    0.07
    alle
    0.07
    ove
    0.06
    Activations Density 0.002%

    No Known Activations