© 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. 111447
    Prev
    Next
    INDEX
    Explanations

    funding

    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
    飨
    -0.28
    íıŃ
    -0.27
    ä¹³
    -0.27
    воз
    -0.25
    _VOL
    -0.24
    amm
    -0.24
    /pkg
    -0.24
    è¯ŀ
    -0.24
     дол
    -0.24
     Fro
    -0.24
    POSITIVE LOGITS
     AUTHORS
    0.27
     Ritch
    0.26
     encour
    0.24
    uploader
    0.24
    gnore
    0.24
    pci
    0.24
    ilestone
    0.23
     Richie
    0.23
     euch
    0.23
    beat
    0.23
    Activations Density 0.004%

    No Known Activations