© 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. 8167
    Prev
    Next
    INDEX
    Explanations

    Common English words

    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
    D
    -0.28
    亢
    -0.28
    ä½įäºİ
    -0.28
    ç½ij讯
    -0.27
    shire
    -0.27
    åĭº
    -0.26
    ç®
    -0.26
    M
    -0.25
    Free
    -0.25
    e
    -0.24
    POSITIVE LOGITS
     narrowed
    0.27
    icare
    0.27
    flation
    0.25
    .relative
    0.24
    æĪijæīį
    0.24
    ippers
    0.24
    плав
    0.24
    çªĦ
    0.23
     narrowly
    0.23
    Truthy
    0.23
    Activations Density 0.032%

    No Known Activations