© 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. 7666
    Prev
    Next
    INDEX
    Explanations

    causal inference and effects

    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
    лÑĮÑĤи
    -0.08
     visi
    -0.08
    ohana
    -0.08
    åīįæµ·
    -0.08
    raje
    -0.07
    <dim
    -0.07
     competit
    -0.07
    空头
    -0.07
    -wrapper
    -0.07
    å°Ķå¤ļ
    -0.07
    POSITIVE LOGITS
     causal
    0.15
    åĽłæŀľ
    0.15
    åĽłæŀľåħ³ç³»
    0.14
     caus
    0.12
     inference
    0.09
     attribution
    0.09
     пÑĢиÑĩин
    0.09
    Cause
    0.08
     Cause
    0.08
    åħ³ç³»çļĦ
    0.08
    Activations Density 0.037%

    No Known Activations