© 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. 30428
    Prev
    Next
    INDEX
    Explanations

    Questions asking "Do you want..."

    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
     обо
    -0.27
    éķķ
    -0.27
    æ²ŁéĢļ
    -0.27
     Nähe
    -0.26
    èĽĶ
    -0.26
    è¾ĩ
    -0.26
    æijĦ
    -0.25
     effected
    -0.24
     confiscated
    -0.24
    æķ£çĥŃ
    -0.24
    POSITIVE LOGITS
    åºĶä»ĺ
    0.28
     statistic
    0.28
    çĶ©
    0.26
    åľ¨æł¡
    0.26
    alon
    0.26
    æĵį
    0.25
     strugg
    0.25
    ioneer
    0.25
    node
    0.24
    yll
    0.24
    Activations Density 0.807%

    No Known Activations