© 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. 5765
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    {@
    -0.27
    relevant
    -0.26
    pard
    -0.26
    è¯¥æł¡
    -0.25
     }}">{{
    -0.25
    åī§ä¸Ń
    -0.25
    visor
    -0.24
    åı¦ä¸Ģä½į
    -0.24
    [P
    -0.24
    并ä¸įå¤ļ
    -0.23
    POSITIVE LOGITS
    mentation
    0.29
     ceasefire
    0.27
    ssue
    0.26
    ç¢ij
    0.25
     ARTICLE
    0.25
    驹
    0.25
    ège
    0.25
    æĸ¹å½¢
    0.24
     DIY
    0.24
    ución
    0.23
    Activations Density 0.029%

    No Known Activations