© 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. 40914
    Prev
    Next
    INDEX
    Explanations

    Conditional statements ("if", "whether")

    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
    >Create
    -0.26
    åĬŁ
    -0.26
    æīĵäºĨ
    -0.26
     knocked
    -0.25
    addin
    -0.25
    ponsive
    -0.24
     createTime
    -0.24
    еÑģÑĤи
    -0.24
    gó
    -0.24
     Found
    -0.24
    POSITIVE LOGITS
    quist
    0.27
     Newton
    0.25
    lide
    0.25
    ä»Ģä¹Īåij¢
    0.25
    梨
    0.25
    åı·åı¬
    0.24
     valves
    0.24
    çľº
    0.24
    สล
    0.23
     past
    0.23
    Activations Density 0.400%

    No Known Activations