© 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. 129724
    Prev
    Next
    INDEX
    Explanations

    Scientific and technical texts

    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
    clinic
    -0.28
    =length
    -0.26
    urally
    -0.26
    -te
    -0.25
    rum
    -0.24
    DED
    -0.24
    åħ·æľīä¸Ģå®ļ
    -0.24
    eted
    -0.24
    .BackgroundColor
    -0.23
     ()
    -0.23
    POSITIVE LOGITS
    飧
    0.29
     incons
    0.28
    ervas
    0.26
    TestCase
    0.25
    åŃ½
    0.25
    çĶ¥
    0.25
    (cp
    0.25
    èĭ±æīį
    0.24
     served
    0.24
    ijn
    0.24
    Activations Density 68.110%

    No Known Activations