© 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. 20-TRANSCODER-HP
    7. 107709
    Prev
    Next
    INDEX
    Explanations

    medicine and health risks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪij们çļĦ
    -0.27
    绿èī²åıijå±ķ
    -0.26
     our
    -0.26
    çļĦåºĶçĶ¨
    -0.26
    éĢļåħ³
    -0.26
    çļĦçłĶåıij
    -0.25
    HER
    -0.24
    รà¸ĩ
    -0.24
    绿èī²çݯä¿Ŀ
    -0.24
    Printing
    -0.24
    POSITIVE LOGITS
    udas
    0.29
    å°Ħ
    0.26
    -Disposition
    0.25
    å§Ķ
    0.25
    移åĪ°
    0.25
    å²Ľ
    0.24
     orientations
    0.24
    andro
    0.24
    éĺ»åĬĽ
    0.23
    åįĬå²Ľ
    0.23
    Activations Density 9.553%

    No Known Activations