© 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. 97585
    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
    æīģ
    -0.30
    moth
    -0.25
    ikal
    -0.24
     bat
    -0.24
    åįķä½į
    -0.24
    èįij
    -0.23
     representative
    -0.23
     cá»Ń
    -0.23
    åıijçĥŃ
    -0.23
     may
    -0.22
    POSITIVE LOGITS
    两ä½į
    0.27
    ©½
    0.25
    åıĶ
    0.24
     trailing
    0.23
    sand
    0.23
     Ashe
    0.23
    æĸ°éĹ»åıijå¸ĥ
    0.23
    plex
    0.23
     Saras
    0.23
    eliac
    0.23
    Activations Density 0.077%

    No Known Activations

    This feature has no known activations.