© 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. 120
    Prev
    Next
    INDEX
    Explanations

    last

    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
    伤çĹħ
    -0.32
    åķĦ
    -0.26
    agation
    -0.25
    .defer
    -0.25
    éģ¥
    -0.25
     MEM
    -0.25
    igated
    -0.24
     veg
    -0.24
    Simulation
    -0.24
     Io
    -0.24
    POSITIVE LOGITS
     subject
    0.25
     candidate
    0.25
    åĽłä¸ºä»ĸ们
    0.24
    Be
    0.24
     instrument
    0.24
    åħ´è¶£
    0.23
    头èĦij
    0.23
    leurs
    0.22
    /bower
    0.22
     begr
    0.22
    Activations Density 1.789%

    No Known Activations