© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6311
    Prev
    Next
    INDEX
    Explanations

    It

    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
     dew
    -0.27
    æĬĬ她
    -0.26
    Mob
    -0.25
    zin
    -0.25
     peculiar
    -0.25
    hog
    -0.24
     xu
    -0.24
     Drag
    -0.24
    tron
    -0.24
    åı£è¯Ń
    -0.24
    POSITIVE LOGITS
    lder
    0.27
    åıĮè¾¹
    0.26
     Principle
    0.25
    @stop
    0.24
    åľ°åĮºçļĦ
    0.24
    åľ°åĮº
    0.24
     setDate
    0.23
    setType
    0.23
    /hash
    0.23
    acoes
    0.23
    Activations Density 0.007%

    No Known Activations