© 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. 29487
    Prev
    Next
    INDEX
    Explanations

    Sections and steps

    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
    Not in Any Lists

    No Comments

    Negative Logits
    翼
    -0.32
    ervices
    -0.28
     Stake
    -0.27
    wick
    -0.26
    ough
    -0.25
    éŃij
    -0.25
     manufactures
    -0.25
     stake
    -0.25
    æ£Ĥ
    -0.25
    MAKE
    -0.24
    POSITIVE LOGITS
    ibern
    0.27
    .deploy
    0.26
     kos
    0.26
    çĻ»
    0.26
    ÃŃv
    0.26
    æĴŃåĩº
    0.25
    _pull
    0.25
    ança
    0.25
    enberg
    0.25
    aza
    0.24
    Activations Density 3.138%

    No Known Activations