© 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. 305
    Prev
    Next
    INDEX
    Explanations

    over

    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
     CultureInfo
    -0.01
    urally
    -0.01
     Kara
    -0.01
    gram
    -0.01
    quartered
    -0.01
    bnb
    -0.01
    thumbs
    -0.01
     Thumb
    -0.01
    hone
    -0.01
    ÑģÑĤавка
    -0.01
    POSITIVE LOGITS
    rij
    0.01
    unan
    0.01
    berger
    0.01
     forwards
    0.01
    istique
    0.01
    å°ĺ
    0.01
    lijk
    0.01
    æĪ¢
    0.01
     backward
    0.01
    åĬ²
    0.01
    Activations Density 0.012%

    No Known Activations