© 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. 19-TRANSCODER-HP
    7. 4996
    Prev
    Next
    INDEX
    Explanations

    Beginning of words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fr
    -0.27
    æĬĹçĻĮ
    -0.25
    óg
    -0.25
    efa
    -0.25
    events
    -0.24
    das
    -0.24
     Political
    -0.24
    await
    -0.24
     turnout
    -0.24
    åĪ°æľŁ
    -0.23
    POSITIVE LOGITS
    ucks
    0.25
    ioni
    0.25
     apprec
    0.25
    unders
    0.24
     AFL
    0.24
    icer
    0.23
    åĬŁèĥ½æĢ§
    0.23
     fle
    0.23
    ãĤ³ãĥ³ãĥĨãĥ³
    0.23
    ä½ľäºĨ
    0.23
    Activations Density 0.006%

    No Known Activations