© 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. 63962
    Prev
    Next
    INDEX
    Explanations

    Locations, people and abbreviations

    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
    羯
    -0.27
    oleans
    -0.27
    phia
    -0.26
     readline
    -0.25
    hop
    -0.24
    -pill
    -0.24
    adier
    -0.24
    ogi
    -0.24
    ught
    -0.24
    irk
    -0.23
    POSITIVE LOGITS
    æĹ¢æĺ¯
    0.26
     deriv
    0.26
    çĤĬ
    0.26
    ä½ĵåĪ¶
    0.25
    raud
    0.25
    power
    0.24
    MES
    0.24
    orno
    0.24
    ãĥijãĥ¯ãĥ¼
    0.24
     abstract
    0.24
    Activations Density 4.744%

    No Known Activations