© 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. 8604
    Prev
    Next
    INDEX
    Explanations

    ot

    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
    ilies
    -0.28
     seab
    -0.26
    åį
    -0.25
    ax
    -0.25
    unlink
    -0.25
     NRF
    -0.25
    Fixed
    -0.24
    ç´į
    -0.24
     unre
    -0.24
    oline
    -0.24
    POSITIVE LOGITS
    eya
    0.27
    -ticket
    0.27
    åĭ¾
    0.27
    èµ°å¾Ĺ
    0.27
    交æİ¥
    0.25
    åIJĦ项
    0.24
    å¿Ĩ
    0.24
    并åıij
    0.24
    _VARS
    0.24
    çŃĶé¢ĺ
    0.24
    Activations Density 0.090%

    No Known Activations