© 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. 8214
    Prev
    Next
    INDEX
    Explanations

    Linking, relationships, connections

    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
    ãģĹãĤĩãģĨ
    -0.26
    ä¸Ģ个好çļĦ
    -0.26
    oha
    -0.25
    said
    -0.24
    Thunk
    -0.23
    çļĦ带é¢Ĩ
    -0.22
    ä¸Ģ个æĸ°çļĦ
    -0.22
     piss
    -0.22
    æĶ»åĬ¿
    -0.22
    :init
    -0.21
    POSITIVE LOGITS
    '
    0.36
    "
    0.33
    (
    0.30
    -
    0.29
    ↵
    0.29
    č↵
    0.28
    ing
    0.28
    *
    0.27
    _
    0.27
    ’
    0.27
    Activations Density 5.134%

    No Known Activations