© 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. 163463
    Prev
    Next
    INDEX
    Explanations

    Duration or purpose phrases

    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
    -validator
    -0.31
     moderately
    -0.27
    icap
    -0.27
    çķ¥æľī
    -0.27
    à¸ģะ
    -0.26
    ä¸Ģ个æĺŁæľŁ
    -0.25
    nero
    -0.25
     erv
    -0.25
     mornings
    -0.25
    综åIJĪå¾ģ
    -0.25
    POSITIVE LOGITS
    ä¸ĢçĶŁ
    0.31
     Lifetime
    0.30
     cuá»Ļc
    0.30
    ä¸Ģè¾ĪåŃIJ
    0.30
    çĶŁåij½åij¨æľŁ
    0.30
    å°ĨæĿ¥
    0.30
     lifetime
    0.30
     Future
    0.29
     future
    0.29
    cur
    0.29
    Activations Density 0.002%

    No Known Activations