© 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. 29232
    Prev
    Next
    INDEX
    Explanations

    in

    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
    äºĨ解
    -0.27
    éĿ©åij½
    -0.26
    yk
    -0.26
    wear
    -0.26
    iator
    -0.26
    Fuse
    -0.25
    kad
    -0.25
    åĵĴ
    -0.24
    zos
    -0.24
    èijij
    -0.24
    POSITIVE LOGITS
    oster
    0.26
    é¾Ł
    0.26
    ork
    0.26
    _DISK
    0.25
    _busy
    0.24
    çĭłæĬĵ
    0.24
    åįł
    0.24
     sue
    0.24
     Scot
    0.24
    ABCDEFGHIJKLMNOP
    0.23
    Activations Density 2.020%

    No Known Activations