© 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. 24005
    Prev
    Next
    INDEX
    Explanations

    Nanometers/small measurements

    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
    ann
    -0.26
     BUS
    -0.25
    å¹³åı°ä¸Ĭ
    -0.25
    upo
    -0.24
    åħ¶æ¬¡
    -0.24
    ynchronous
    -0.23
    Exposed
    -0.23
    -cond
    -0.23
    avers
    -0.23
    ynchronously
    -0.23
    POSITIVE LOGITS
     regained
    0.28
    prox
    0.25
    Åij
    0.24
    vides
    0.24
    (holder
    0.24
     ap
    0.23
     dzieci
    0.23
    obra
    0.23
     surface
    0.23
    å»ĵ
    0.23
    Activations Density 0.004%

    No Known Activations