© 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. 24-TRANSCODER-HP
    7. 149404
    Prev
    Next
    INDEX
    Explanations

    ADHD and hyperactivity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ALER
    -0.27
    ãĤĴåĪ©çĶ¨ãģĹãģ¦
    -0.25
    åħ°èĬ±
    -0.24
    çĪ±
    -0.24
    _ROUT
    -0.24
     ratings
    -0.24
    个å¤ļå°ıæŶ
    -0.24
    è¾ľ
    -0.24
    äºİæĺ¯æĪij
    -0.23
    è¿Ļæĸ¹éĿ¢
    -0.23
    POSITIVE LOGITS
    ceive
    0.29
    è¶Ĭ
    0.28
    owski
    0.28
    ''
    0.27
    家åºŃ
    0.25
    æĪ¾
    0.25
     Solomon
    0.25
    ç´¯
    0.24
    å¹²æī°
    0.24
    ])]
    0.24
    Activations Density 0.021%

    No Known Activations