© 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. 18-TRANSCODER-HP
    7. 88264
    Prev
    Next
    INDEX
    Explanations

    Products and projects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ResponseType
    -0.33
    纲
    -0.29
    ä¸ĭä¸Ģ个
    -0.28
    imen
    -0.25
    éļ§éģĵ
    -0.25
    antz
    -0.25
    assen
    -0.24
    è§Ħç¨ĭ
    -0.24
    ạn
    -0.24
    éĢ»è¾ij
    -0.24
    POSITIVE LOGITS
    Left
    0.28
     left
    0.28
     Machines
    0.25
    icial
    0.25
     kostenlos
    0.24
     Left
    0.24
     thru
    0.24
    [min
    0.23
    left
    0.23
     kle
    0.23
    Activations Density 1.626%

    No Known Activations