© 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. 98903
    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
    eff
    -0.26
    ös
    -0.24
    >{@
    -0.23
    è«
    -0.23
    igin
    -0.23
     wells
    -0.23
     persistent
    -0.22
    ÅĤÄħ
    -0.22
     paper
    -0.22
     generalized
    -0.22
    POSITIVE LOGITS
    itzer
    0.27
     BBB
    0.25
    婦
    0.24
    ðŁijĨ
    0.24
    MAND
    0.24
    xBA
    0.24
    LTE
    0.24
    åĴĮ个人
    0.23
    scal
    0.23
    å®ļæŶ
    0.23
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.