© 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. 22-TRANSCODER-HP
    7. 88742
    Prev
    Next
    INDEX
    Explanations

    Source code/licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _PI
    -0.30
    åIJĮåѦ们
    -0.26
    以人为
    -0.25
    gers
    -0.25
    .pose
    -0.24
     Da
    -0.24
     Else
    -0.24
    åĵĪåĵĪ
    -0.24
    °F
    -0.23
     findOne
    -0.23
    POSITIVE LOGITS
    essential
    0.33
    ilinear
    0.27
    jis
    0.27
     essential
    0.26
    bes
    0.26
    opt
    0.26
    icies
    0.26
    unas
    0.26
    etic
    0.25
    à¹īà¸Ńà¸ĩ
    0.25
    Activations Density 0.008%

    No Known Activations