© 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. 45137
    Prev
    Next
    INDEX
    Explanations

    visual elements or representations

    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
    andel
    -0.08
    kv
    -0.07
    ipo
    -0.07
    isti
    -0.06
    .ads
    -0.06
     hitch
    -0.06
    ivec
    -0.06
     arc
    -0.06
    #ad
    -0.06
    繫
    -0.06
    POSITIVE LOGITS
     visual
    0.10
    è¦ĸ覺
    0.09
    visual
    0.09
    è§Ĩè§ī
    0.09
    .visual
    0.08
     visualize
    0.08
     visually
    0.08
     визÑĥалÑĮно
    0.08
     Visual
    0.08
    缴è§ĤçļĦæĸ¹å¼ı
    0.08
    Activations Density 0.010%

    No Known Activations