© 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. 99255
    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
    поÑĢ
    -0.24
     perse
    -0.24
     glac
    -0.23
    éĿŀè¦ģ
    -0.23
    æĻĴ
    -0.23
    escal
    -0.22
    åıij表
    -0.22
    riad
    -0.22
     unresolved
    -0.22
    à¹īว
    -0.22
    POSITIVE LOGITS
    TEL
    0.27
    verty
    0.27
    hg
    0.27
    èĢģ年人
    0.26
    ono
    0.25
    emaakt
    0.25
    gt
    0.24
    çĸĶ
    0.23
    rama
    0.23
    yt
    0.23
    Activations Density 0.816%

    No Known Activations

    This feature has no known activations.