© 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. 163372
    Prev
    Next
    INDEX
    Explanations

    death

    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
    -times
    -0.28
     hÆ°á»Ľng
    -0.26
     ref
    -0.26
     steer
    -0.25
    orr
    -0.25
    entlich
    -0.24
    orc
    -0.24
    磶
    -0.24
    æĭĪ
    -0.24
    oldt
    -0.24
    POSITIVE LOGITS
    ä¿ı
    0.29
     irres
    0.28
    -powered
    0.27
     powered
    0.26
    饰åĵģ
    0.26
    æºIJæ³ī
    0.26
    æľīä¸ĢçĤ¹
    0.25
    hw
    0.25
    powered
    0.24
     lig
    0.24
    Activations Density 0.004%

    No Known Activations