© 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. 24077
    Prev
    Next
    INDEX
    Explanations

    unincorporated communities/places

    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
    个
    -0.32
     raft
    -0.30
     prob
    -0.27
    ä¸Ģèĩ´
    -0.27
     Ih
    -0.27
    quals
    -0.26
     gradu
    -0.26
    个å°ı
    -0.26
     Gov
    -0.25
    ä¸Ģ个
    -0.25
    POSITIVE LOGITS
    ularity
    0.27
    æ¸İ
    0.27
    æĩĭ
    0.27
    EEP
    0.26
    éĥĬåĮº
    0.26
    thora
    0.26
    MASK
    0.25
    _Delay
    0.25
    çĶŁæ´»æ°´å¹³
    0.24
     Satisfaction
    0.24
    Activations Density 0.005%

    No Known Activations