© 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. 130177
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ibilities
    -0.26
    dag
    -0.26
    顺
    -0.26
    odos
    -0.25
    eba
    -0.25
    ноÑģÑĤей
    -0.25
    balances
    -0.25
    amac
    -0.25
    ials
    -0.25
     sheet
    -0.25
    POSITIVE LOGITS
    èµ°ä¸ĭåİ»
    0.26
    åĺ§
    0.24
    åįĥæĸ¹
    0.24
     rigged
    0.24
    对ä¸įèµ·
    0.24
     manifold
    0.23
    åĽłä¸ºä½ł
    0.23
    ä¸ĩ欧åħĥ
    0.23
    åĿª
    0.23
     TripAdvisor
    0.23
    Activations Density 0.095%

    No Known Activations

    This feature has no known activations.