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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 109
    Prev
    Next
    INDEX
    Explanations

    da/daemon/medical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºı
    -0.25
    assa
    -0.25
    ä¸įå¼Ģ
    -0.24
    çŀ¿
    -0.24
    arent
    -0.24
    亲å±ŀ
    -0.23
    åħīåѦ
    -0.23
    rats
    -0.23
    é¥
    -0.23
     Till
    -0.22
    POSITIVE LOGITS
    wed
    0.28
    -figure
    0.25
    ainer
    0.25
    yk
    0.23
     excav
    0.23
    æĸ°å±ĢéĿ¢
    0.22
    æ¥Ķ
    0.22
     cultivation
    0.22
    insky
    0.22
    åıijçİ°äºĨ
    0.22
    Activations Density 0.097%

    No Known Activations