© 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. 163185
    Prev
    Next
    INDEX
    Explanations

    similar

    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
    åħĪ
    -0.29
    æľ¬
    -0.27
    æķĻ
    -0.27
    æĶ¶
    -0.27
    stead
    -0.27
    ä¹³
    -0.27
    åħĪè¿Ľ
    -0.26
    igu
    -0.26
    agg
    -0.25
    ision
    -0.25
    POSITIVE LOGITS
    ä¼¼
    0.28
    angkan
    0.26
     giá»ijng
    0.25
    ãģ¨åIJĮãģĺ
    0.25
     lifes
    0.25
     @{↵
    0.25
     counterpart
    0.25
    çĭ¸
    0.24
    æīĵæī®
    0.24
    .rank
    0.24
    Activations Density 0.014%

    No Known Activations