© 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. 7876
    Prev
    Next
    INDEX
    Explanations

    -like

    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
    loo
    -0.26
    orro
    -0.25
     unins
    -0.24
    лин
    -0.24
    -lined
    -0.23
    undi
    -0.23
     ÑĥдаÑĢ
    -0.23
    itters
    -0.23
    udents
    -0.23
    itored
    -0.23
    POSITIVE LOGITS
     précis
    0.25
    /feed
    0.25
    osh
    0.24
    bose
    0.24
    bucket
    0.24
    åĬ¿
    0.24
    å°Ķ
    0.23
    åħ¥ãĤĮ
    0.23
    .beh
    0.23
     tear
    0.23
    Activations Density 0.319%

    No Known Activations