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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89567
    Prev
    Next
    INDEX
    Explanations

    Varied data types/text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľ¬äºº
    -0.30
    åĩºä»»
    -0.28
    ivot
    -0.28
    eter
    -0.28
     who
    -0.28
     brothers
    -0.27
    个人
    -0.26
    erez
    -0.26
    åĴĮä»ĸçļĦ
    -0.26
     Merlin
    -0.25
    POSITIVE LOGITS
    æĸĩåĮĸ建设
    0.27
    éĽĨä½ĵ
    0.26
    åħ¬åı¸å°Ĩ
    0.25
    itory
    0.25
    æĺ¯ä¸Ģéĥ¨
    0.25
    管çIJĨæĿ¡ä¾ĭ
    0.25
    mint
    0.25
    åĪĨæĪIJ
    0.24
    éĩĮéĿ¢æľī
    0.24
    ctions
    0.24
    Activations Density 49.902%

    No Known Activations