© 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. 7715
    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
    ORITY
    -0.28
     undisclosed
    -0.26
    ·
    -0.26
    以èī²
    -0.26
     merit
    -0.26
     ÑĦай
    -0.25
    èµ·æĿ¥äºĨ
    -0.25
    eros
    -0.25
     Coalition
    -0.24
     merging
    -0.24
    POSITIVE LOGITS
    ogne
    0.29
     EG
    0.27
    ingle
    0.26
    éĻIJ
    0.25
    gle
    0.25
     rut
    0.25
     Eg
    0.25
     E
    0.25
    akra
    0.25
    ä¸ĵåĮº
    0.25
    Activations Density 0.006%

    No Known Activations