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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5418
    Prev
    Next
    INDEX
    Explanations

    coding, math

    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
    çĽĺ
    -0.26
    åĨįä¸Ģ次
    -0.26
     somehow
    -0.25
    åĽ´
    -0.25
     plunge
    -0.24
    æĥŁ
    -0.24
    Again
    -0.24
    iaux
    -0.23
    祷
    -0.23
     plung
    -0.23
    POSITIVE LOGITS
    fern
    0.31
    eya
    0.26
    echa
    0.25
    åĺ¿åĺ¿
    0.25
    asics
    0.25
     conserv
    0.25
    ä¸įä¿¡
    0.24
    çľĭä»ĸ
    0.24
    äº
    0.23
    asco
    0.23
    Activations Density 0.894%

    No Known Activations