© 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. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53819
    Prev
    Next
    INDEX
    Explanations

    ordinal terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Junior
    -0.31
     Principal
    -0.29
    æĤ£èĢħ
    -0.28
    Principal
    -0.28
    .synthetic
    -0.27
    Senior
    -0.27
    umba
    -0.27
    rec
    -0.26
    overe
    -0.26
     principal
    -0.26
    POSITIVE LOGITS
    first
    0.44
    第ä¸Ģ
    0.43
     first
    0.42
    第ä¸Ģ个
    0.39
    .first
    0.37
    第ä¸ĢèĬĤ
    0.35
    çļĦ第ä¸Ģ
    0.33
    第ä¸Ģéĥ¨
    0.33
    第ä¸Ģ次
    0.32
     current
    0.31
    Activations Density 0.047%

    No Known Activations