© 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. 22-TRANSCODER-HP
    7. 131143
    Prev
    Next
    INDEX
    Explanations

    refine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    gun
    -0.27
     ấy
    -0.27
    éĤ£æŶ
    -0.23
     Kund
    -0.23
    ä¸Ģ身
    -0.23
    rend
    -0.23
    ftime
    -0.22
    丰
    -0.22
     filmed
    -0.22
    çĸ«æĥħ
    -0.22
    POSITIVE LOGITS
    eting
    0.28
    ering
    0.27
    ERING
    0.27
    eted
    0.26
     fluid
    0.26
     heat
    0.26
    amental
    0.26
    à¤
    0.25
     matter
    0.25
     turf
    0.25
    Activations Density 0.086%

    No Known Activations