© 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. 24262
    Prev
    Next
    INDEX
    Explanations

    PCB

    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
     uc
    -0.26
    opo
    -0.25
    oliday
    -0.25
    ead
    -0.25
    çIJ¢
    -0.24
     torrent
    -0.24
     Kens
    -0.24
     encountering
    -0.23
     rain
    -0.23
    BUFF
    -0.23
    POSITIVE LOGITS
    æ°Ľ
    0.29
    èģļ
    0.26
     irreversible
    0.25
    lotte
    0.25
    ç³ľ
    0.25
     irr
    0.24
    ä¸Ń举
    0.24
    иÑĢованиÑı
    0.24
    Ir
    0.24
    åĭŁ
    0.24
    Activations Density 0.002%

    No Known Activations