© 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. 5188
    Prev
    Next
    INDEX
    Explanations

    epidemi

    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
    è¿Ļä¸ĢçĤ¹
    -0.32
    onis
    -0.29
    ãģĵãģ¨ãģĮãģ§ãģįãģ¾ãģĻ
    -0.24
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.24
    è¿ĻçĤ¹
    -0.24
    ignon
    -0.24
    裸
    -0.23
    mdir
    -0.23
    éĹ³
    -0.23
    cter
    -0.23
    POSITIVE LOGITS
    ous
    0.28
     abroad
    0.27
     beyond
    0.24
    embed
    0.23
    æĦĪ
    0.23
     thr
    0.22
     Singer
    0.22
    adj
    0.22
     ¡
    0.22
     sine
    0.22
    Activations Density 0.761%

    No Known Activations