© 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. 89719
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    æ´ŀå¯Ł
    -0.28
    ermo
    -0.27
    {:
    -0.25
    /left
    -0.25
     corp
    -0.25
     reflections
    -0.25
     {:
    -0.25
    æĭ§
    -0.24
    æŃ¼
    -0.24
    èį¼
    -0.24
    POSITIVE LOGITS
    ocking
    0.30
    æľĪ份
    0.26
    efault
    0.26
     backlight
    0.25
    acking
    0.24
    çĹ
    0.24
    æłĿ
    0.24
    axe
    0.24
    Exc
    0.24
    elp
    0.23
    Activations Density 20.704%

    No Known Activations