© 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. 7544
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    ecture
    -0.25
    æľŁåĨħ
    -0.24
    rans
    -0.23
     convinced
    -0.23
    arrant
    -0.23
     appropriate
    -0.23
    erti
    -0.23
    uitable
    -0.23
    roman
    -0.22
     evidence
    -0.22
    POSITIVE LOGITS
    éĤ£ä¸ªæŶåĢĻ
    0.27
    mó
    0.26
    setQuery
    0.24
    DDR
    0.24
    /license
    0.24
    ì¦Ī
    0.23
    éĤ£æŶåĢĻ
    0.23
    olson
    0.23
    daemon
    0.23
    主åĬ¨æĢ§
    0.23
    Activations Density 1.353%

    No Known Activations