© 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. 112475
    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
     bottom
    -0.29
    vent
    -0.25
    ow
    -0.25
    åħ¸
    -0.25
    warm
    -0.25
    éļħ
    -0.24
     tph
    -0.24
     reverse
    -0.24
    æī¬
    -0.23
    acci
    -0.23
    POSITIVE LOGITS
     Gathering
    0.27
    çī¢è®°ä½¿åij½
    0.25
    friend
    0.25
    uya
    0.24
    ocard
    0.24
     Nev
    0.24
    家ä¼Ļ
    0.24
     Justi
    0.24
    ÅĤow
    0.24
    .pkg
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.