© 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. 57407
    Prev
    Next
    INDEX
    Explanations

    structured or technical information

    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
    èİ«æĸ¯ç§ij
    -0.27
    okin
    -0.27
    glob
    -0.27
    æ±ł
    -0.26
    okit
    -0.26
     mbedtls
    -0.25
     pool
    -0.24
    .pool
    -0.24
    æĥ³åİ»
    -0.24
    ¡
    -0.23
    POSITIVE LOGITS
    atta
    0.29
     Flower
    0.28
    ·æĸ°
    0.27
    æĤħ
    0.27
     Flowers
    0.27
    æĤŁ
    0.26
    æŃ¥
    0.26
    associate
    0.26
    驸
    0.26
     abstract
    0.25
    Activations Density 0.001%

    No Known Activations