© 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. 19-TRANSCODER-HP
    7. 7914
    Prev
    Next
    INDEX
    Explanations

    possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīĺ管
    -0.25
    à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    -0.25
    è¿Ļ家ä¼Ļ
    -0.25
    å
    -0.24
    å®ĥåı¯ä»¥
    -0.24
    å©Ĭ
    -0.23
    RAFT
    -0.23
    .hy
    -0.23
    art
    -0.23
    cg
    -0.23
    POSITIVE LOGITS
    说æľį
    0.29
     solemn
    0.28
    inkle
    0.28
     Holt
    0.28
    zos
    0.28
    继
    0.28
    æł¸
    0.26
    åĬĽæ±Ĥ
    0.26
    ibbon
    0.26
    affe
    0.26
    Activations Density 0.065%

    No Known Activations