© 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. 108002
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    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
    lemen
    -0.27
    arbeit
    -0.26
    structor
    -0.26
     domina
    -0.26
     Cros
    -0.24
     ↵    ↵
    -0.24
    ENTER
    -0.24
    OUN
    -0.24
    .ErrorCode
    -0.24
    åĽĽèĤ¢
    -0.24
    POSITIVE LOGITS
    æİ¥åıĹ
    0.28
    æİ¥åıĹäºĨ
    0.26
    ibase
    0.26
    绿èī²åıijå±ķ
    0.26
    ç»Ĩèħ»
    0.25
     accept
    0.25
    propri
    0.25
     ci
    0.25
     thus
    0.25
    涣
    0.25
    Activations Density 6.124%

    No Known Activations