© 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. 18-TRANSCODER-HP
    7. 89183
    Prev
    Next
    INDEX
    Explanations

    Code structure/syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nullptr
    -0.27
     specifier
    -0.27
    uhan
    -0.26
    .newaxis
    -0.26
    ë²Īíĺ¸
    -0.25
    åĢĻ
    -0.24
     nullptr
    -0.24
     thÆ°Æ¡ng
    -0.24
    çĨŁ
    -0.24
     Sahara
    -0.24
    POSITIVE LOGITS
    ç»Ħ
    0.27
    lich
    0.27
    bit
    0.25
    åŀĤ
    0.25
    éĩĮ
    0.24
    lim
    0.24
    ancel
    0.24
    ç¼Ľ
    0.24
    инÑĭ
    0.24
     Up
    0.23
    Activations Density 13.686%

    No Known Activations