© 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. 97215
    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
    Negative Logits
    @section
    -0.27
     poj
    -0.26
    ิà¸ĩ
    -0.24
    èݹ
    -0.23
     rig
    -0.23
    åij¨å¹´
    -0.23
    zeigen
    -0.23
    æ³³
    -0.23
    çļĵ
    -0.22
    __).
    -0.22
    POSITIVE LOGITS
     guilt
    0.25
    idl
    0.24
    guards
    0.24
    iners
    0.23
    æĤĴ
    0.23
    éĴµ
    0.22
    -ap
    0.22
    ॥
    0.22
    .PL
    0.22
    åİĭæĬij
    0.22
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.