© 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. 5976
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    anel
    -0.27
    è¿Ļ两个
    -0.27
    æ¯Ľ
    -0.26
    elter
    -0.25
    chen
    -0.25
    è¿Ļ两
    -0.24
    uib
    -0.24
     coun
    -0.24
     Proposition
    -0.24
     What
    -0.23
    POSITIVE LOGITS
    çĶŁç´ł
    0.28
    ä¼ijæģ¯
    0.27
    лÑĮÑĨ
    0.25
    swith
    0.24
    åħ¬æĬ¥
    0.24
    墨西åĵ¥
    0.24
    icker
    0.24
    worth
    0.24
    áŀģ
    0.24
    ä¹ĺ车
    0.23
    Activations Density 0.080%

    No Known Activations