© 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. 130546
    Prev
    Next
    INDEX
    Explanations

    research abstracts

    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
    éĩįè¦ģåĨħ容
    -0.27
    éĢģåĩº
    -0.26
    omp
    -0.25
     optionally
    -0.24
    åĪ°çİ°åľ¨
    -0.24
    Latest
    -0.24
     kidding
    -0.24
    ModelIndex
    -0.24
    è´¥
    -0.23
    edly
    -0.23
    POSITIVE LOGITS
    çĥŁåĽ±
    0.27
    åľ°ä¸Ĭ
    0.26
    olumbia
    0.25
    åħ¨å¸Ĥ
    0.24
    顶
    0.24
    èĺ¸
    0.24
    åĬ³åĬ¨
    0.23
    .pipe
    0.23
    -os
    0.23
    çŃı
    0.23
    Activations Density 0.224%

    No Known Activations