© 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. 9262
    Prev
    Next
    INDEX
    Explanations

    misunderstanding or missing something

    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
    éģ¿åħįåĽł
    -0.08
    âu
    -0.07
    éĹ®åĮ»çĶŁ
    -0.07
    kins
    -0.07
    ä¸įåĢ¦
    -0.07
    orgia
    -0.07
    ä¸įæķ£
    -0.07
    udas
    -0.06
    ارة
    -0.06
     franca
    -0.06
    POSITIVE LOGITS
     interpretations
    0.07
    解读
    0.07
    LETTE
    0.07
     interpretación
    0.07
    .Parser
    0.07
    ATUS
    0.07
    åĴ
    0.07
     interpretation
    0.07
    夥
    0.07
    icom
    0.07
    Activations Density 0.051%

    No Known Activations