© 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. 8093
    Prev
    Next
    INDEX
    Explanations

    web content snippets

    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
    gers
    -0.29
    геÑĢ
    -0.26
    arta
    -0.26
     estimating
    -0.25
     moy
    -0.24
    iction
    -0.24
    ï¾Ł
    -0.24
    acades
    -0.24
     Wheat
    -0.24
     MLA
    -0.24
    POSITIVE LOGITS
    åĵº
    0.29
    åı£ä¸Ń
    0.26
    ä¿¡
    0.25
    chos
    0.25
    ique
    0.25
     Dur
    0.25
     processes
    0.25
    ix
    0.24
    Dur
    0.24
    unct
    0.24
    Activations Density 0.004%

    No Known Activations