© 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. 130644
    Prev
    Next
    INDEX
    Explanations

    Names of people/places

    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
     populations
    -0.26
    大åºĨ
    -0.25
     ont
    -0.25
    aff
    -0.25
     Hutchinson
    -0.25
    AAP
    -0.24
     classified
    -0.24
     annihil
    -0.23
    .isEnabled
    -0.23
     involved
    -0.23
    POSITIVE LOGITS
    工夫
    0.27
    æ¯ĶåĪ©
    0.27
    秤
    0.26
    éĶı
    0.26
    wil
    0.26
     mái
    0.25
    sher
    0.24
    é¢ĩ为
    0.24
    æ´½
    0.24
    ois
    0.24
    Activations Density 3.772%

    No Known Activations