© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7119
    Prev
    Next
    INDEX
    Explanations

    code/documentation text

    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
    榫
    -0.26
    tat
    -0.25
     ben
    -0.25
    缨
    -0.24
    tim
    -0.24
    cpy
    -0.23
    ä¸įäºĨ解
    -0.23
    第äºĮæī¹
    -0.22
    æĥħåĨµè¿Ľè¡Į
    -0.22
    baugh
    -0.22
    POSITIVE LOGITS
    ÑģÑĤа
    0.27
    erno
    0.26
    st
    0.25
    .swing
    0.25
    æĢ»
    0.24
    atable
    0.24
    adoo
    0.24
    çĸ²æĥ«
    0.24
    è·ĥ
    0.23
    istro
    0.23
    Activations Density 2.447%

    No Known Activations