© 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. 9-TRANSCODER-HP
    7. 30198
    Prev
    Next
    INDEX
    Explanations

    residence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ulus
    -0.28
    uisse
    -0.28
    enschaft
    -0.27
    istinguished
    -0.26
    /XMLSchema
    -0.26
    obel
    -0.26
    addColumn
    -0.25
    æĿľåħ°
    -0.25
    unts
    -0.24
    :params
    -0.24
    POSITIVE LOGITS
    forge
    0.29
     bay
    0.28
    /packages
    0.27
     hyp
    0.27
    Bay
    0.26
     Bay
    0.26
     hanging
    0.26
    åĽ¾çĶ»
    0.25
    æĤ¬
    0.25
     wik
    0.25
    Activations Density 0.541%

    No Known Activations