© 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. 365
    Prev
    Next
    INDEX
    Explanations

    be

    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
    hapus
    -0.26
    naire
    -0.26
    uÃŃ
    -0.25
    ez
    -0.24
    nez
    -0.24
    uento
    -0.24
    iembre
    -0.24
    URED
    -0.23
    åĸĶ
    -0.23
    subscription
    -0.23
    POSITIVE LOGITS
    æĦıè§ģåıįé¦Ī
    0.27
    åİŁæłĩé¢ĺ
    0.26
    âĿ
    0.25
     mistaken
    0.25
     way
    0.24
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.24
    initWith
    0.24
     gently
    0.24
     helf
    0.24
     lif
    0.24
    Activations Density 0.037%

    No Known Activations