© 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. 163292
    Prev
    Next
    INDEX
    Explanations

    keep

    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
    ä½ĵä¼ļ
    -0.28
    격
    -0.27
    ẻ
    -0.26
    ä¹Łå¥½
    -0.25
     chops
    -0.24
    alytics
    -0.24
    abor
    -0.24
    çĿĢåĬĽ
    -0.24
    ä¸ŃåįİæĸĩåĮĸ
    -0.24
    ackage
    -0.24
    POSITIVE LOGITS
     wast
    0.29
    ForObject
    0.28
    OKEN
    0.26
    åĮºåŁŁåĨħ
    0.26
     synonymous
    0.25
    containers
    0.25
     remotely
    0.24
     together
    0.24
     combined
    0.24
    mad
    0.24
    Activations Density 0.007%

    No Known Activations