© 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. 64175
    Prev
    Next
    INDEX
    Explanations

    coding/technical reports

    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
    å¾½
    -0.26
    est
    -0.24
    ÑĢаг
    -0.24
    éģĤ
    -0.24
    eger
    -0.24
     XS
    -0.24
    Ø·ÙĨ
    -0.24
    aternity
    -0.23
    ÑĤÑı
    -0.23
    еле
    -0.23
    POSITIVE LOGITS
    éĤ£äºĽ
    0.32
     those
    0.31
    those
    0.26
    缸è¿ŀ
    0.26
     ones
    0.26
     instances
    0.26
    åķ¤
    0.25
    è¿Ļéĥ¨åĪĨ
    0.24
    .instances
    0.24
    ä¸Ģåī¯
    0.24
    Activations Density 23.339%

    No Known Activations