© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89648
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reductions
    -0.31
     reduction
    -0.30
    è¿ĺä¸įæĺ¯
    -0.29
    cox
    -0.27
    carrier
    -0.27
    åīĬåĩı
    -0.26
    æĸ¯åŁº
    -0.26
     Reduction
    -0.26
    åĩıå°ijäºĨ
    -0.25
     reduced
    -0.25
    POSITIVE LOGITS
    ide
    0.28
     Contacts
    0.27
    ily
    0.27
    iest
    0.27
     Pot
    0.26
    åĽ½æ°ij
    0.26
    å°ģéĿ¢
    0.25
    contacts
    0.25
    ı
    0.24
     steer
    0.24
    Activations Density 7.836%

    No Known Activations