© 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. 99075
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     Beh
    -0.26
    æĢ»åħ¬åı¸
    -0.25
    .Decimal
    -0.25
    woord
    -0.25
    Dic
    -0.25
     Correspond
    -0.24
     Pert
    -0.24
     Corpus
    -0.24
    好åĩłä¸ª
    -0.23
    çĶŁäº§æĢ»
    -0.23
    POSITIVE LOGITS
    èĪªçıŃ
    0.28
    éĿĴ
    0.26
     swe
    0.26
    ufe
    0.26
     fr
    0.26
     biod
    0.26
    ueue
    0.25
     mer
    0.25
    born
    0.25
    amente
    0.25
    Activations Density 0.026%

    No Known Activations