© 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. 111703
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical abstracts

    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
    çľĭå¾ħ
    -0.27
    å»·
    -0.27
    illus
    -0.26
     endforeach
    -0.26
    kbd
    -0.26
    æĻ¾
    -0.25
    elay
    -0.25
     billions
    -0.25
     emptied
    -0.25
    sealed
    -0.24
    POSITIVE LOGITS
     ion
    0.27
    -c
    0.26
    ashi
    0.25
    doch
    0.24
     teammate
    0.24
    TION
    0.23
    upon
    0.23
     Michele
    0.23
     technology
    0.23
    .onStart
    0.23
    Activations Density 0.104%

    No Known Activations