© 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. 27-TRANSCODER-HP
    7. 56748
    Prev
    Next
    INDEX
    Explanations

    "omet"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hort
    -0.29
    ylene
    -0.27
    ork
    -0.25
    æĮĸ
    -0.25
    تÙĬÙĨ
    -0.24
    edi
    -0.24
    urat
    -0.24
    ity
    -0.24
    åħ·æľīä¸Ģå®ļ
    -0.24
    æ±īæĹı
    -0.23
    POSITIVE LOGITS
    人æµģ
    0.31
    omba
    0.28
    ä¸ĩ
    0.28
    mere
    0.25
    antro
    0.25
    bitcoin
    0.25
    -side
    0.25
    pered
    0.25
    andon
    0.25
    ä½ľåĩº
    0.24
    Activations Density 1.076%

    No Known Activations