© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162759
    Prev
    Next
    INDEX
    Explanations

    Executive leadership

    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
    åıĮåIJij
    -0.27
    BY
    -0.26
    ===
    -0.26
    欢è¿İæĤ¨
    -0.26
    æ§Į
    -0.25
     pedest
    -0.25
    rowser
    -0.25
    /use
    -0.24
    è¿ijå¹´
    -0.24
    åħ¸åŀĭæ¡Īä¾ĭ
    -0.24
    POSITIVE LOGITS
    æľīæķĪæĢ§
    0.28
    urus
    0.26
     Prince
    0.25
    -head
    0.25
     Wis
    0.25
    Prince
    0.25
     fallout
    0.24
     affairs
    0.23
    irector
    0.23
    iele
    0.23
    Activations Density 0.021%

    No Known Activations