© 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. 107852
    Prev
    Next
    INDEX
    Explanations

    Questions and documentation

    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
    геÑĢ
    -0.27
    locker
    -0.26
    adjusted
    -0.26
    åı¦ä¸Ģè¾¹
    -0.26
    èµ°è¿ĩ
    -0.25
     ([[
    -0.25
    å¿«
    -0.24
    iane
    -0.24
    çľĭ好
    -0.24
    èĬ±èįī
    -0.24
    POSITIVE LOGITS
     crea
    0.24
    ONO
    0.23
    ottage
    0.23
     obr
    0.23
    ä½ķ
    0.23
    Tri
    0.23
     Äijòi
    0.23
     Company
    0.23
    vection
    0.23
    :Any
    0.23
    Activations Density 3.240%

    No Known Activations