© 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. 162462
    Prev
    Next
    INDEX
    Explanations

    conditional words

    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
    dm
    -0.29
    æĪĸå°Ĩ
    -0.28
     æĪĸ
    -0.24
    ảng
    -0.24
    mars
    -0.24
    涵
    -0.24
    éĺģ
    -0.24
     Fern
    -0.23
    æĪĸ
    -0.23
     åŃĹ
    -0.23
    POSITIVE LOGITS
     very
    0.29
    ências
    0.27
    hape
    0.26
    acles
    0.25
    rog
    0.24
    æĵ¿
    0.24
    ohen
    0.24
    heel
    0.24
    äºī论
    0.24
    人æĢ§
    0.23
    Activations Density 0.006%

    No Known Activations