© 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. 32-TRANSCODER-HP
    7. 43420
    Prev
    Next
    INDEX
    Explanations

    wholesale and trading

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èįĩ
    -0.29
     Äijen
    -0.28
    ä½ľèĢħæľ¬äºº
    -0.26
    Unified
    -0.26
    .testng
    -0.26
    hay
    -0.25
    -inverse
    -0.24
    à¹Ħหล
    -0.24
    AVIS
    -0.24
     szczególn
    -0.23
    POSITIVE LOGITS
     brand
    0.32
     whe
    0.30
     exporter
    0.29
     race
    0.29
     distribution
    0.29
    导
    0.28
     Distrib
    0.28
    ä¸ŃéĹ´
    0.28
    åĵģçīĮ
    0.28
     exported
    0.27
    Activations Density 0.004%

    No Known Activations