© 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. 4-TRANSCODER-HP
    7. 188
    Prev
    Next
    INDEX
    Explanations

    elevated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eny
    -0.26
     verm
    -0.26
     [{↵
    -0.25
    è¥¿çº¢æŁ¿
    -0.25
    ä¸ĢæŃ¥
    -0.25
    ç¼Ģ
    -0.25
    æĪij们认为
    -0.25
    .ResponseBody
    -0.25
     alle
    -0.24
    .bd
    -0.24
    POSITIVE LOGITS
    egot
    0.29
    istant
    0.28
    lasses
    0.28
    äºĨèĩªå·±çļĦ
    0.25
    åŁºæķ°
    0.25
    heim
    0.25
    istas
    0.24
    è£ħéħįå¼ı
    0.24
    /stat
    0.24
    æ¹į
    0.24
    Activations Density 0.121%

    No Known Activations