© 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. 8515
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     pros
    -0.27
    ä¹ĥ
    -0.26
    erner
    -0.25
    äºĭ项
    -0.25
    mpz
    -0.25
     pro
    -0.25
    uan
    -0.24
    ä¹ħ
    -0.24
    è¿Ľåİ»
    -0.24
    edin
    -0.24
    POSITIVE LOGITS
    olley
    0.30
    åīĬ
    0.29
    ilege
    0.27
    leet
    0.27
    cul
    0.26
    mmas
    0.25
    inear
    0.25
    æĬķ稿
    0.24
    /Create
    0.24
     Ksi
    0.24
    Activations Density 0.121%

    No Known Activations

    This feature has no known activations.