© 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. 163239
    Prev
    Next
    INDEX
    Explanations

    use

    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
     whenever
    -0.33
     in
    -0.30
    ompson
    -0.28
    å®ĥ
    -0.27
     during
    -0.27
    æѤæĸĩ
    -0.27
    äºİ
    -0.27
    essim
    -0.26
     glColor
    -0.26
     elsewhere
    -0.25
    POSITIVE LOGITS
    ivan
    0.27
    çļĦå°±æĺ¯
    0.26
    åĩºå¤Ħ
    0.24
    ä¼ļ让
    0.23
    .liferay
    0.23
    è´£
    0.23
    MISSION
    0.23
     vet
    0.23
     Graz
    0.23
     bÃło
    0.23
    Activations Density 0.012%

    No Known Activations