© 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. 54201
    Prev
    Next
    INDEX
    Explanations

    developing countries and economies

    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
     Exclude
    -0.27
    _wire
    -0.27
    zap
    -0.26
    ^K
    -0.26
    +w
    -0.25
    iras
    -0.25
    é£Ĵ
    -0.25
    éĶĨ
    -0.25
    Exclude
    -0.25
    uyo
    -0.25
    POSITIVE LOGITS
    度
    0.31
     degrees
    0.30
    üm
    0.28
     degree
    0.27
     href
    0.26
    åħ¨åĽ½
    0.26
    ute
    0.25
    ä¸ĭ
    0.25
    PLEX
    0.25
    åĪĨ享
    0.25
    Activations Density 0.016%

    No Known Activations