© 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. 63628
    Prev
    Next
    INDEX
    Explanations

    Comparisons or sequences

    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
    ewood
    -0.28
    PEnd
    -0.27
     Own
    -0.26
    lew
    -0.25
    ends
    -0.25
    iquement
    -0.25
    <Q
    -0.24
    <System
    -0.23
    æ±Ĥ
    -0.23
    èİ·æī¹
    -0.23
    POSITIVE LOGITS
    è²Į
    0.24
    ивание
    0.24
    iah
    0.24
    strom
    0.24
    ItemType
    0.24
    icc
    0.24
    omo
    0.23
    éĨĩ
    0.23
    Stamp
    0.23
    js
    0.23
    Activations Density 13.550%

    No Known Activations