© 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. 8790
    Prev
    Next
    INDEX
    Explanations

    new

    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
     dirs
    -0.27
    ensible
    -0.25
    /no
    -0.25
     corrid
    -0.24
     fullPath
    -0.24
    Borders
    -0.24
    å¤
    -0.24
    pite
    -0.24
    FFE
    -0.23
    plemented
    -0.23
    POSITIVE LOGITS
    _ready
    0.25
     hun
    0.25
    çļĦä¸Ģ项
    0.25
    ?><
    0.25
    installer
    0.24
    astes
    0.24
    atz
    0.24
    æ±ĩ
    0.24
    ins
    0.23
    Await
    0.23
    Activations Density 0.013%

    No Known Activations