© 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. 180
    Prev
    Next
    INDEX
    Explanations

    names

    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
    sam
    -0.32
    è¹´
    -0.28
    avl
    -0.27
    INGER
    -0.26
     stalled
    -0.26
    åħ¬å®īå±Ģ
    -0.25
    éļį
    -0.25
    åķ¡
    -0.24
    s
    -0.24
    bed
    -0.24
    POSITIVE LOGITS
    åľ°åĿª
    0.24
    ofile
    0.23
    çŃ¾åŃĹ
    0.23
    çłĶ究ä¸Ńå¿ĥ
    0.23
    {/*
    0.22
     Composition
    0.22
     reduced
    0.22
    rats
    0.21
     Rodriguez
    0.21
    =__
    0.21
    Activations Density 0.022%

    No Known Activations