© 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. 8317
    Prev
    Next
    INDEX
    Explanations

    Abbreviated organization names

    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
    åĪ¤
    -0.27
     organise
    -0.26
     pund
    -0.26
    ä¸ĢæŦ
    -0.26
    theless
    -0.25
    inois
    -0.25
    ä¸įæĪIJ
    -0.25
    ceive
    -0.25
    å¾Ĺå¾Ī
    -0.24
    ctors
    -0.24
    POSITIVE LOGITS
    å±¥
    0.26
    桧
    0.26
    å±IJ
    0.26
    CNT
    0.25
    (ml
    0.24
    çµķå°į
    0.24
    åįģä½Ļå¹´
    0.24
    ort
    0.24
     GT
    0.24
     bay
    0.23
    Activations Density 0.034%

    No Known Activations