© 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. 163426
    Prev
    Next
    INDEX
    Explanations

    of

    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
    รว
    -0.28
    fter
    -0.27
    å¤ļä½į
    -0.26
    ysize
    -0.26
    ä¸Ģ棵
    -0.26
    @brief
    -0.25
     AtomicInteger
    -0.25
    åıĪ被
    -0.25
    ä¸ĩæĪ·
    -0.25
    åħ¨
    -0.24
    POSITIVE LOGITS
    ç¿»
    0.27
     Labs
    0.27
    æ»ŀ
    0.27
    åij¨è¾¹
    0.25
    uel
    0.25
    iers
    0.25
    çļĦæĹ¥åŃIJ
    0.24
    åĴĮ个人
    0.24
    ilib
    0.24
    erÃŃa
    0.24
    Activations Density 0.002%

    No Known Activations