© 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. 88515
    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
    cé
    -0.29
    ÑıÑĤ
    -0.27
    CF
    -0.24
    аниз
    -0.23
    ifier
    -0.23
    \Framework
    -0.23
    ifiers
    -0.23
    adel
    -0.22
     bulun
    -0.22
    áz
    -0.22
    POSITIVE LOGITS
     bÃło
    0.27
     purposes
    0.27
    onus
    0.26
     icmp
    0.26
    bedo
    0.25
    :class
    0.25
    oland
    0.25
     Purpose
    0.25
     Volk
    0.24
     purpose
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.