© 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
    2. Qwen3-4B
    3. 12-TRANSCODER-HP
    4. 23494
    Prev
    Next
    INDEX
    Explanations

    brief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķij
    -0.28
    china
    -0.25
    _hooks
    -0.25
    ucc
    -0.25
    cu
    -0.24
    ilm
    -0.24
    æĩ·
    -0.24
    umar
    -0.24
    两侧
    -0.23
    æĹłç¼ĺ
    -0.23
    POSITIVE LOGITS
    ieee
    0.27
     chip
    0.25
    launch
    0.25
     dim
    0.24
     autof
    0.24
    详æĥħ
    0.24
    rending
    0.24
    羣å®ŀæĢ§
    0.24
    (to
    0.23
    è¯ķæİ¢
    0.23
    Activations Density 0.003%

    No Known Activations