© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98940
    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
    çĥŁ
    -0.27
    itre
    -0.26
     fatt
    -0.26
     syn
    -0.24
     fal
    -0.24
    è¿·
    -0.24
    次ä¼ļè®®
    -0.24
     kans
    -0.23
    å°Ŀè¯ķ
    -0.23
    THEN
    -0.23
    POSITIVE LOGITS
    ursive
    0.29
    -gay
    0.24
    ceph
    0.24
    为ä½ķ
    0.24
    åĽ½èµĦ
    0.24
    åħ¨é¢Ŀ
    0.23
    igated
    0.23
    zl
    0.23
     Belly
    0.23
    guarded
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.