© 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. 32-TRANSCODER-HP
    7. 40982
    Prev
    Next
    INDEX
    Explanations

    childhood

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Pandora
    -0.30
    hea
    -0.27
    ogui
    -0.27
    ogl
    -0.25
    xEB
    -0.25
    ipse
    -0.25
    ldb
    -0.25
    æīĺ
    -0.24
    itness
    -0.24
    xp
    -0.24
    POSITIVE LOGITS
     childhood
    0.28
     Childhood
    0.26
    童年
    0.26
    室
    0.26
     baby
    0.24
    çºłéĶĻ
    0.24
    å°ıçĶ·åŃ©
    0.24
    ç«¥
    0.24
    æ±Ĭ
    0.23
    iku
    0.23
    Activations Density 0.030%

    No Known Activations