© 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. 30388
    Prev
    Next
    INDEX
    Explanations

    Now

    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
    éIJĺ
    -0.30
     heartbeat
    -0.28
     TER
    -0.27
    pager
    -0.25
     hôn
    -0.25
    alley
    -0.25
    饴
    -0.25
     sexually
    -0.25
     SCHOOL
    -0.24
     ******************************************************************************↵
    -0.24
    POSITIVE LOGITS
    iro
    0.30
    aire
    0.30
    icut
    0.29
    uent
    0.28
    elf
    0.26
    设å®ļ
    0.26
    çĻ¾ä¸ĩ
    0.25
    ç´łæĿIJ
    0.25
    esian
    0.25
    çĻ¾
    0.25
    Activations Density 1.568%

    No Known Activations