© 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. 14-TRANSCODER-HP
    7. 40730
    Prev
    Next
    INDEX
    Explanations

    vital

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¹³åĿ¦
    -0.25
    ãģ¤ãģĦ
    -0.24
    åŁİ乡å±ħæ°ij
    -0.24
    vio
    -0.23
    档次
    -0.23
    .rb
    -0.23
     preference
    -0.23
    æ°ijåĽ½
    -0.23
     sequence
    -0.23
     pard
    -0.23
    POSITIVE LOGITS
    被迫
    0.27
    issance
    0.27
     Unknown
    0.26
     civilizations
    0.25
    PELL
    0.24
    reh
    0.24
    à´´
    0.24
    Unknown
    0.24
     spells
    0.23
    .querySelectorAll
    0.23
    Activations Density 6.672%

    No Known Activations