© 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. 7495
    Prev
    Next
    INDEX
    Explanations

    Technical or informational content

    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
    诸å¦Ĥ
    -0.31
    åĮħæĭ¬
    -0.30
    umped
    -0.30
    åĪĨåĪ«æĺ¯
    -0.29
    lace
    -0.28
    åĪĨåĪ«
    -0.28
    ä¾ĭå¦Ĥ
    -0.28
     including
    -0.26
    åĪĨåĪ«ä¸º
    -0.26
     Lives
    -0.25
    POSITIVE LOGITS
    &q
    0.28
    biz
    0.26
    TÃľ
    0.26
    .createTextNode
    0.26
    æŁIJ个
    0.26
     Biz
    0.25
    osite
    0.24
    åIJ©
    0.24
    bt
    0.24
    .maven
    0.23
    Activations Density 0.076%

    No Known Activations