© 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. 19541
    Prev
    Next
    INDEX
    Explanations

    causal factors or risk factors

    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
    ืà¸Ķ
    -0.08
     Cunning
    -0.08
    ï¼įï¼įï¼įï¼į
    -0.08
    elves
    -0.08
    apas
    -0.07
    æĮij
    -0.07
    å·¡è§Ĩåijĺ
    -0.07
    èIJ©
    -0.07
     Playing
    -0.07
    ersed
    -0.07
    POSITIVE LOGITS
    quis
    0.08
     hallmark
    0.07
     crucial
    0.07
     necessary
    0.07
    常çĶ¨äºİ
    0.07
     essential
    0.07
     traditionally
    0.06
    ä¹ĥ
    0.06
     plag
    0.06
     critical
    0.06
    Activations Density 0.145%

    No Known Activations