© 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. 110986
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    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
     маÑĪ
    -0.26
     ìĿ´ë¥¼
    -0.26
    -org
    -0.25
    æĪijåĽ½
    -0.25
    åĪĽæĸ°
    -0.25
    çĨŁ
    -0.25
    åĽ«
    -0.25
    adapt
    -0.25
     Innovation
    -0.25
    åħ¬å¼ı
    -0.24
    POSITIVE LOGITS
    enk
    0.40
    iel
    0.28
    ainties
    0.26
    ilen
    0.26
     ENC
    0.26
    _('
    0.26
    .intent
    0.25
    entai
    0.25
    essaging
    0.25
    aunch
    0.24
    Activations Density 0.001%

    No Known Activations