© 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. 12-TRANSCODER-HP
    7. 22618
    Prev
    Next
    INDEX
    Explanations

    Forum posts

    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
    umes
    -0.29
    INE
    -0.28
    .Details
    -0.28
    å¼Ł
    -0.27
    uptools
    -0.27
    INES
    -0.26
     whatsoever
    -0.26
    ARK
    -0.26
    erts
    -0.25
    åĴĮ个人
    -0.25
    POSITIVE LOGITS
    ä¾
    0.34
    çĽĨåľ°
    0.26
     WOM
    0.26
    edef
    0.25
    æīĭ段
    0.24
    ColumnInfo
    0.24
    ç½ijç«Ļ建设
    0.24
     Gh
    0.24
    ä¸įåħį
    0.24
    :Is
    0.24
    Activations Density 0.000%

    No Known Activations