© 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. 98620
    Prev
    Next
    INDEX
    Explanations

    The, ordinals, death, ENT

    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
    iot
    -0.29
    mino
    -0.27
    aments
    -0.27
    amental
    -0.27
     Ship
    -0.27
    intr
    -0.27
    оÑģ
    -0.26
    s
    -0.26
    ack
    -0.26
    ture
    -0.26
    POSITIVE LOGITS
    habi
    0.27
    PELL
    0.27
    Forgery
    0.26
    -lfs
    0.26
    ansa
    0.25
    hort
    0.25
     Wolverine
    0.24
    elson
    0.24
    robat
    0.24
     lul
    0.24
    Activations Density 0.004%

    No Known Activations