© 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. 168
    Prev
    Next
    INDEX
    Explanations

    ition

    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
    utely
    -0.26
     umb
    -0.25
    mina
    -0.25
    æ£īèĬ±
    -0.24
    ç²½
    -0.24
    #index
    -0.24
     loin
    -0.23
     states
    -0.23
     cine
    -0.23
     naive
    -0.23
    POSITIVE LOGITS
    éħįåIJĪ
    0.30
    深交
    0.29
     Traffic
    0.28
    plies
    0.26
     WINAPI
    0.25
    endment
    0.25
    ishes
    0.25
    æ¶Įçİ°
    0.24
    vvm
    0.24
    Launcher
    0.24
    Activations Density 0.009%

    No Known Activations