© 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. 24131
    Prev
    Next
    INDEX
    Explanations

    Maryland - Greenbelt

    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
     Belly
    -0.26
     grains
    -0.26
     bliss
    -0.25
    artin
    -0.24
     ench
    -0.24
     preorder
    -0.24
    æĶ¶å®ĺ
    -0.23
    utive
    -0.23
    ANCH
    -0.23
    糧
    -0.23
    POSITIVE LOGITS
    Slf
    0.27
    常
    0.27
    MF
    0.26
    Mos
    0.26
    ä»Ģä¹Īéĥ½
    0.26
     Memor
    0.26
    kes
    0.26
    å·¥ä½ľå²Ĺä½į
    0.26
    TEL
    0.25
    exter
    0.25
    Activations Density 0.000%

    No Known Activations