© 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. 130905
    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
    esp
    -0.29
     esp
    -0.29
    educt
    -0.26
     اÙĦصÙģ
    -0.25
    é«ĺæ¸ħ
    -0.24
    å¤ĸ
    -0.24
     bu
    -0.24
     Esp
    -0.24
    äºİ
    -0.24
    ди
    -0.24
    POSITIVE LOGITS
    åĴĮ个人
    0.29
    çĸı
    0.27
    æĺ¯éŁ©åĽ½
    0.26
    个人
    0.26
    åĩĨ
    0.25
    Aura
    0.25
    æį¢
    0.25
    ä»»ä½ķ人éĥ½
    0.25
    .Anchor
    0.24
    .ca
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.