© 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. 8447
    Prev
    Next
    INDEX
    Explanations

    wall

    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
    åĽ½æĥħ
    -0.23
    bee
    -0.23
    sav
    -0.23
     Regarding
    -0.22
    pps
    -0.22
    åĪļæīį
    -0.22
    Owned
    -0.21
    CCC
    -0.21
     oldest
    -0.21
     segu
    -0.21
    POSITIVE LOGITS
    éĿ¢ç§¯
    0.26
    ãģ¹ãģį
    0.25
    PM
    0.25
    iki
    0.25
    front
    0.24
    æĽĿ
    0.24
    OLID
    0.23
    omat
    0.23
    ripper
    0.23
     dú
    0.23
    Activations Density 2.124%

    No Known Activations