© 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. 5420
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    apo
    -0.29
    inker
    -0.28
     Fir
    -0.27
    alink
    -0.27
    iven
    -0.26
    IVEN
    -0.26
     lasting
    -0.26
    è¿Ļ个游æĪı
    -0.26
    好åIJ§
    -0.26
     Firm
    -0.26
    POSITIVE LOGITS
    èģĨ
    0.30
    æĶ¶èİ·
    0.28
    è½½
    0.28
    ä½Ļ
    0.27
    é¦
    0.27
    cit
    0.27
     hÆ°á»Łng
    0.25
    æĬµ
    0.25
    ä¿®å¤į
    0.24
    éĻ¨
    0.24
    Activations Density 0.040%

    No Known Activations

    This feature has no known activations.