© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112314
    Prev
    Next
    INDEX
    Explanations

    Excerpts from larger texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    aria
    -0.28
    寥
    -0.25
    -ish
    -0.24
    LOUR
    -0.24
     semble
    -0.24
    å¡ijæĸĻ
    -0.24
    ãĤį
    -0.23
     subroutine
    -0.23
    lier
    -0.23
    èijµ
    -0.23
    POSITIVE LOGITS
    ëĵĢ
    0.26
    Ïĥ
    0.25
     excell
    0.25
    formance
    0.24
     Early
    0.24
    artial
    0.24
    (binding
    0.23
    ymm
    0.23
    .guard
    0.23
     XSS
    0.23
    Activations Density 0.003%

    No Known Activations