© 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. 162557
    Prev
    Next
    INDEX
    Explanations

    biom

    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
    ä¸ļ
    -0.27
     Rough
    -0.24
    çļĦçģµéŃĤ
    -0.24
    ä¸Ŀ
    -0.24
    梦幻
    -0.23
    )(((
    -0.23
     <<↵
    -0.23
     Psychological
    -0.23
    天é¹ħ
    -0.23
    гÑĢад
    -0.23
    POSITIVE LOGITS
     infrastructure
    0.33
     hardware
    0.33
     physical
    0.32
    硬件
    0.31
     spatial
    0.28
     Physical
    0.27
    åŁºç¡Ģ设æĸ½
    0.27
     infra
    0.27
    kur
    0.27
     geometric
    0.26
    Activations Density 0.005%

    No Known Activations