© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142063
    Prev
    Next
    INDEX
    Explanations

    insight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICATION
    -0.25
    å¤ĦåĪĨ
    -0.25
    bidden
    -0.25
    he
    -0.23
    ena
    -0.23
    hab
    -0.23
    holm
    -0.23
    usted
    -0.22
    æī«ä¸Ģ
    -0.22
    lore
    -0.22
    POSITIVE LOGITS
     embr
    0.27
    ypes
    0.26
    anggal
    0.25
    bjerg
    0.24
    ATES
    0.24
     alike
    0.24
     neighbouring
    0.23
    éı¡
    0.23
    iate
    0.23
    æł²
    0.23
    Activations Density 16.330%

    No Known Activations