© 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. 130352
    Prev
    Next
    INDEX
    Explanations

    Unstructured, random text

    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
     blinds
    -0.29
    ereal
    -0.28
    ãĥ¥ãĥ¼
    -0.27
    ackle
    -0.26
     rubbish
    -0.26
    饰
    -0.25
    ruise
    -0.25
     Deal
    -0.25
     Rosie
    -0.25
    èij¬
    -0.25
    POSITIVE LOGITS
    ary
    0.29
    ...
    0.28
    MAP
    0.27
    æ¦Ĩ
    0.26
     such
    0.26
    .↵
    0.25
    éĽģ
    0.25
    .Map
    0.24
     reversible
    0.24
    _imp
    0.24
    Activations Density 1.556%

    No Known Activations