© 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. 29102
    Prev
    Next
    INDEX
    Explanations

    publications and edits

    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
    Entered
    -0.27
    /tree
    -0.26
    éĩį大
    -0.25
    æľĢ大åĮĸ
    -0.25
    NEL
    -0.25
    raise
    -0.25
    çĶŁæŃ»
    -0.25
    å¤Ħç½®
    -0.24
    chl
    -0.24
     Til
    -0.24
    POSITIVE LOGITS
    eteria
    0.27
    âĢ¥
    0.26
    çŃĭ
    0.26
    æµģè¡Į
    0.25
     Robert
    0.25
    ica
    0.25
    ffen
    0.24
    Robert
    0.24
     jobs
    0.24
    æµģè¡ĮçļĦ
    0.24
    Activations Density 2.748%

    No Known Activations