© 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. 130984
    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
     single
    -0.26
    ataka
    -0.25
     Behaviour
    -0.25
    ingle
    -0.24
    /share
    -0.24
    word
    -0.24
    ccount
    -0.24
     ÑģÑĤеп
    -0.23
    ãĥ¢ãĥĩ
    -0.23
    stant
    -0.23
    POSITIVE LOGITS
    åĩłä¸ªæľĪ
    0.27
    é¾Ħ
    0.27
    æ°ij主çĶŁæ´»
    0.24
    çĦĺ
    0.24
     tmpl
    0.23
     willen
    0.23
     privé
    0.23
    Granted
    0.22
     helicopt
    0.22
    _requires
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.