© 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. 130235
    Prev
    Next
    INDEX
    Explanations

    before and after

    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
    åĩłå®¶
    -0.35
    åĢŁ
    -0.28
    bower
    -0.25
    planes
    -0.25
     planes
    -0.24
    ellular
    -0.24
    plane
    -0.24
    igation
    -0.24
    .nasa
    -0.24
    åIJĦæĸ¹
    -0.23
    POSITIVE LOGITS
    éĻį
    0.28
    quee
    0.28
    actor
    0.26
    halb
    0.26
    _drv
    0.26
    æ®ĸ
    0.25
     reproduction
    0.25
    research
    0.25
    éĨĽ
    0.25
    é±¼
    0.25
    Activations Density 5.031%

    No Known Activations