© 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. 163361
    Prev
    Next
    INDEX
    Explanations

    Expressing concerns

    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
    pawn
    -0.28
    gre
    -0.28
     اÙĦØ£Ùħ
    -0.26
     OTHERWISE
    -0.25
    Weekly
    -0.24
    imers
    -0.24
    chie
    -0.24
    YPE
    -0.24
    legates
    -0.24
    说æĪij
    -0.24
    POSITIVE LOGITS
    ä¹Łæĺ¯ä¸Ģ个
    0.28
    åĩŃçĿĢ
    0.28
    æŀŀ
    0.27
    æķĿ
    0.25
     knowledge
    0.25
    RAL
    0.25
    èµĸ
    0.25
    /lic
    0.25
    çļĦçŁ¥è¯Ĩ
    0.24
    ).__
    0.24
    Activations Density 0.004%

    No Known Activations