© 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. 23-TRANSCODER-HP
    7. 163490
    Prev
    Next
    INDEX
    Explanations

    Vietnamese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŁķ
    -0.29
    ä»ĸæĺ¯ä¸Ģ个
    -0.29
    äºĨä»ĸçļĦ
    -0.29
    为æĤ¨
    -0.28
     imposing
    -0.27
    Eastern
    -0.27
    æŀĭ
    -0.26
    Cho
    -0.25
    æį
    -0.24
    ning
    -0.24
    POSITIVE LOGITS
    å¨ģ
    0.29
    çĽ²
    0.28
     blind
    0.28
    keiten
    0.27
    ĪæĿĥ
    0.26
    åİĭ
    0.26
    äºij
    0.26
    端
    0.26
    ÅĤo
    0.25
    æľª
    0.25
    Activations Density 0.004%

    No Known Activations