© 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. 12-TRANSCODER-HP
    7. 24199
    Prev
    Next
    INDEX
    Explanations

    Volts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rido
    -0.26
    ieu
    -0.25
    uite
    -0.24
    åĺ´
    -0.24
    åľ°ä¸Ń
    -0.24
     Crane
    -0.23
    åĩºåİ»
    -0.23
    ningen
    -0.23
    inality
    -0.23
    Terminal
    -0.23
    POSITIVE LOGITS
    æĿ¥åģļ
    0.32
    sville
    0.28
    *X
    0.27
    åħ®
    0.27
    ulton
    0.26
    __(*
    0.26
    æĿ¥åĪ°
    0.26
    yo
    0.25
    éļIJéļIJ
    0.25
     instantiated
    0.25
    Activations Density 0.006%

    No Known Activations