© 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. 162446
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific writing

    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
    åģļè¿ĩ
    -0.26
    chwitz
    -0.25
    ẩm
    -0.25
    composite
    -0.25
    æĪijè¿ĺ
    -0.24
    eated
    -0.24
    rying
    -0.24
    ä¸Ģæŀļ
    -0.24
    .AddColumn
    -0.24
    agged
    -0.24
    POSITIVE LOGITS
     is
    0.40
    æĺ¯ä»Ģä¹Īåij¢
    0.36
    æĺ¯
    0.35
     uniquely
    0.34
    ↵↵
    0.32
     ise
    0.32
     are
    0.31
     unique
    0.31
    æĺ¯ä¸Ģç§į
    0.31
    åĪĻæĺ¯
    0.31
    Activations Density 0.002%

    No Known Activations