© 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. 8037
    Prev
    Next
    INDEX
    Explanations

    pose

    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
    çīĪ
    -0.24
     ApplicationController
    -0.24
    quiv
    -0.24
    sizes
    -0.22
    flows
    -0.22
    lands
    -0.22
    ħ§
    -0.21
    ilers
    -0.21
    ippers
    -0.21
    ivité
    -0.21
    POSITIVE LOGITS
    ä¸Ģå®ļçļĦ
    0.26
     lifelong
    0.25
    aul
    0.24
    åµĺ
    0.23
    ative
    0.23
    严峻
    0.22
     dangling
    0.22
    åĽłåľ°åĪ¶å®ľ
    0.22
    /compiler
    0.21
    主æĿĥ
    0.21
    Activations Density 1.807%

    No Known Activations