© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7221
    Prev
    Next
    INDEX
    Explanations

    Code/introductions/titles

    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
     hex
    -0.28
    wing
    -0.28
     palm
    -0.26
    iche
    -0.25
    hex
    -0.24
    æ£ķ
    -0.24
    atively
    -0.24
    èľ»
    -0.24
     rocking
    -0.23
     tiles
    -0.23
    POSITIVE LOGITS
     precisely
    0.28
     Prec
    0.25
    Variables
    0.24
     quienes
    0.23
     precis
    0.23
    .vars
    0.23
    arkan
    0.23
    æīī
    0.22
    utom
    0.22
    manage
    0.22
    Activations Density 0.044%

    No Known Activations