© 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. 33-TRANSCODER-HP
    7. 54813
    Prev
    Next
    INDEX
    Explanations

    childhood trauma and stress

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ares
    -0.27
    å½±è§Ĩåī§
    -0.26
    imens
    -0.26
     Loose
    -0.25
    Svg
    -0.25
    SizeMode
    -0.25
    út
    -0.25
    _att
    -0.24
    kart
    -0.24
    ANTS
    -0.24
    POSITIVE LOGITS
     mutual
    0.29
    æķĻèĤ²
    0.29
    æķĻèĤ²èµĦæºIJ
    0.28
    rij
    0.27
     call
    0.26
    缸äºĴ
    0.26
     relationship
    0.26
    call
    0.26
    æ»ĭ
    0.26
    æ±²
    0.25
    Activations Density 0.028%

    No Known Activations