© 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. 8979
    Prev
    Next
    INDEX
    Explanations

    technical/legal documents

    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
     guys
    -0.28
     бÑĥк
    -0.28
    mers
    -0.27
    å¯Įè£ķ
    -0.27
     worthy
    -0.26
     workout
    -0.25
    oyer
    -0.25
    oplay
    -0.24
    <Renderer
    -0.24
    Watcher
    -0.24
    POSITIVE LOGITS
    åħļåĨħ
    0.28
     egreg
    0.28
     onFinish
    0.27
    isma
    0.26
     Nev
    0.25
    ')])↵
    0.25
    riere
    0.25
    âĦ
    0.25
    istles
    0.24
    BEST
    0.24
    Activations Density 0.021%

    No Known Activations