© 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. 185
    Prev
    Next
    INDEX
    Explanations

    AF

    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
    ião
    -0.29
    çļĦ妻åŃIJ
    -0.28
    .conf
    -0.26
    ç¼ľ
    -0.25
    ⣦
    -0.24
    Expanded
    -0.23
    æľĢ好æĺ¯
    -0.23
     Pret
    -0.23
    IBUT
    -0.23
    éªŀ
    -0.23
    POSITIVE LOGITS
     claw
    0.28
    æĮĩçĶ²
    0.27
    èµ°åĩº
    0.25
    èµ°åĩºæĿ¥
    0.25
    catch
    0.24
     curtains
    0.24
     comm
    0.24
    atches
    0.24
     nú
    0.24
    alez
    0.23
    Activations Density 0.017%

    No Known Activations