© 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. 112074
    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
    丰å¯Į
    -0.26
     likely
    -0.25
    indle
    -0.25
     program
    -0.24
    UDIO
    -0.24
     Likely
    -0.24
     bund
    -0.24
    PACK
    -0.24
    滥
    -0.24
    bud
    -0.23
    POSITIVE LOGITS
    enic
    0.26
    çªģå¦Ĥåħ¶æĿ¥
    0.25
     Spit
    0.25
    interval
    0.25
    TEM
    0.25
    'S
    0.25
    uj
    0.24
    natal
    0.24
     outer
    0.24
    lr
    0.24
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.