© 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. 29310
    Prev
    Next
    INDEX
    Explanations

    Dog breeds

    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
    åħ¥å¢ĥ
    -0.28
    isel
    -0.28
    åīįèĢħ
    -0.26
    çĿĢçľ¼
    -0.26
    aky
    -0.26
     rab
    -0.25
    详æĥħ
    -0.25
    leys
    -0.25
    iforn
    -0.25
    inka
    -0.25
    POSITIVE LOGITS
    BLOCK
    0.27
    -major
    0.26
     Major
    0.25
    ls
    0.24
     cushions
    0.24
    _PROJECT
    0.24
    模èĮĥ
    0.24
     Vox
    0.24
    hort
    0.24
    -block
    0.24
    Activations Density 1.499%

    No Known Activations