© 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. 8853
    Prev
    Next
    INDEX
    Explanations

    Code, dates, numbers

    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
    endant
    -0.26
    çĻ½é©¬
    -0.25
     wann
    -0.24
     DESCRIPTION
    -0.23
    ä¸įåĩº
    -0.23
    preh
    -0.23
     Ack
    -0.23
     Analyst
    -0.22
    ÑĮÑı
    -0.22
     Anal
    -0.22
    POSITIVE LOGITS
    forg
    0.26
    WXYZ
    0.25
     navig
    0.24
    éĹ¾
    0.24
     rem
    0.24
    osal
    0.23
    adors
    0.23
    ResourceManager
    0.23
     navigate
    0.23
    NAV
    0.23
    Activations Density 0.121%

    No Known Activations