© 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. 20-TRANSCODER-HP
    7. 130241
    Prev
    Next
    INDEX
    Explanations

    environmental systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancial
    -0.27
    али
    -0.26
    idenav
    -0.26
    ande
    -0.25
    /help
    -0.24
     Kodi
    -0.23
    /null
    -0.23
     ↵    ↵
    -0.23
    aty
    -0.23
    ÑĮ
    -0.23
    POSITIVE LOGITS
    íıī
    0.28
     exh
    0.28
    åħ«å¤§
    0.26
    çĨ¨
    0.26
    etail
    0.26
    à¸ģำ
    0.24
    eurs
    0.24
    ÐĴидео
    0.24
    fix
    0.24
     {[
    0.24
    Activations Density 3.298%

    No Known Activations