© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30250
    Prev
    Next
    INDEX
    Explanations

    code/technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĥŀ
    -0.27
    ä¸Ģ个æĺ¯
    -0.27
     scenes
    -0.27
    ATHER
    -0.26
    èĤł
    -0.26
    主æĴŃ
    -0.25
    è²Į
    -0.24
     spoiler
    -0.23
    æĥĬ
    -0.23
    scene
    -0.23
    POSITIVE LOGITS
    ifetime
    0.25
    积累
    0.25
    alk
    0.25
    ÂŃi
    0.24
    nex
    0.24
     mechanism
    0.23
    åijĬè¯ī大家
    0.23
    iko
    0.23
    æĭ±
    0.23
     beet
    0.23
    Activations Density 3.258%

    No Known Activations