© 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. 1454
    Prev
    Next
    INDEX
    Explanations

    causal inference mediation effect

    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
    nyi
    -0.07
    ÏĥοÏħ
    -0.07
    ceaux
    -0.07
    å®ļåŀĭ
    -0.07
    olÃŃ
    -0.07
    <|box_end|>
    -0.07
    ykk
    -0.07
    èĬ±ä¸Ģ
    -0.07
    æ¡ĤåĨł
    -0.07
     consec
    -0.07
    POSITIVE LOGITS
     causal
    0.10
     caus
    0.08
    åĽłæŀľ
    0.08
     downstream
    0.07
     paths
    0.07
     pipelines
    0.07
    æĺ¯çĽ´æİ¥
    0.07
    raca
    0.07
    åĽłæŀľåħ³ç³»
    0.07
    è¾Ī
    0.07
    Activations Density 0.011%

    No Known Activations