© 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. 5370
    Prev
    Next
    INDEX
    Explanations

    personal narratives

    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
    etto
    -0.30
     Ideally
    -0.25
    åİ»çľĭçľĭ
    -0.25
    inv
    -0.24
     neutrality
    -0.24
     tort
    -0.24
    ä¼Łå¤§çļĦ
    -0.24
    é¢ĵ
    -0.24
    etro
    -0.23
    art
    -0.23
    POSITIVE LOGITS
    ç»Ļä½ł
    0.35
     suggestion
    0.31
    ç»ĻæĪij
    0.31
    建议
    0.31
     suggestions
    0.31
    å¸®ä½ł
    0.29
    ç»ĻæĪij们
    0.28
    å¯¹ä½ł
    0.27
    ç§ģãģĮ
    0.26
    èįIJ
    0.26
    Activations Density 0.021%

    No Known Activations