© 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. 98633
    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
    vÃŃ
    -0.27
    alloc
    -0.26
    ents
    -0.26
    æĢĿèĢĥ
    -0.26
    VML
    -0.25
    æĢĿç´¢
    -0.25
    éĻĩ
    -0.24
    ali
    -0.24
    upa
    -0.24
    æij¸ç´¢
    -0.24
    POSITIVE LOGITS
    >{!!
    0.28
    ivos
    0.26
    å¤įå·¥
    0.26
    arkin
    0.25
    terms
    0.25
    (Sub
    0.25
    _BLOCKS
    0.25
    tero
    0.24
    heiten
    0.24
     Highly
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.