© 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. 24219
    Prev
    Next
    INDEX
    Explanations

    Locations in India

    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
    .clips
    -0.27
    çݩ家æĿ¥è¯´
    -0.26
    å«©
    -0.25
    ç»ĵå±Ģ
    -0.25
    æĸ°ä¸ī
    -0.25
    æŀ¯çĩ¥
    -0.25
    olo
    -0.25
     outcome
    -0.25
    inters
    -0.25
    raphics
    -0.24
    POSITIVE LOGITS
    æŶæĬ¥
    0.29
    IBC
    0.24
    uchar
    0.24
    urn
    0.24
    ullah
    0.24
     Escorts
    0.24
     Definitions
    0.23
    yar
    0.23
     contested
    0.23
    IAM
    0.23
    Activations Density 0.009%

    No Known Activations