© 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. 141834
    Prev
    Next
    INDEX
    Explanations

    complex, technical language

    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
    ç²¾ç¥ŀ
    -0.31
    èĬ±æł·
    -0.27
    伯
    -0.26
    à¹Ħà¸ĭ
    -0.25
    anax
    -0.24
    表æĺİ
    -0.24
    anine
    -0.24
    onical
    -0.23
    éĽĨ
    -0.23
    Spec
    -0.23
    POSITIVE LOGITS
    oir
    0.31
    ¡°
    0.27
    -plugins
    0.27
    éĺ»
    0.27
    çĺ¤
    0.26
    æŁŀ
    0.25
    _mm
    0.25
    PAL
    0.24
    iston
    0.24
    ocrat
    0.24
    Activations Density 13.690%

    No Known Activations