© 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. 20-TRANSCODER-HP
    7. 107719
    Prev
    Next
    INDEX
    Explanations

    Research, studies, software, medical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¡°
    -0.26
    éĻ£
    -0.26
     Slots
    -0.26
    éĩİ
    -0.25
    antically
    -0.24
     SLOT
    -0.24
    ordon
    -0.24
    ãģ«åħ¥ãĤĮ
    -0.24
    çĶ¨æĪ·æıIJä¾Ľ
    -0.24
     slots
    -0.23
    POSITIVE LOGITS
     concat
    0.26
     ogr
    0.26
    etta
    0.25
    å®ľ
    0.25
    âĸĪâĸĪâĸĪâĸĪ
    0.25
    è¾Ľ
    0.24
     MPH
    0.23
     ring
    0.23
     leven
    0.23
    abble
    0.23
    Activations Density 1.499%

    No Known Activations