© 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. 27-TRANSCODER-HP
    7. 58217
    Prev
    Next
    INDEX
    Explanations

    legal, documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪĸèĢħ说
    -0.27
    sti
    -0.26
    ãĢģ“
    -0.25
     dataArray
    -0.25
    SError
    -0.25
    æĪĸèĢħæĺ¯
    -0.24
    åħ¬å¼Ģåıijè¡Į
    -0.24
    ories
    -0.24
    .datas
    -0.24
    ceased
    -0.24
    POSITIVE LOGITS
    æİĪ
    0.30
    AFE
    0.29
     than
    0.29
    èµĭ
    0.28
    çŃĭ
    0.27
    æīĭ
    0.26
     Palo
    0.26
     Than
    0.25
    åĿ¦
    0.25
    ä¹ĭæĺŁ
    0.25
    Activations Density 0.021%

    No Known Activations