© 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. 40907
    Prev
    Next
    INDEX
    Explanations

    Unstructured text

    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
    ivil
    -0.25
     Defaults
    -0.25
     Constructs
    -0.25
    æĬķèµĦ人
    -0.25
     fetched
    -0.25
    Õª
    -0.25
    éĨĮ
    -0.24
     Constraints
    -0.23
    bial
    -0.23
     picturesque
    -0.23
    POSITIVE LOGITS
    å»ī
    0.29
    èīī
    0.28
    æİĪ课
    0.26
    çļĦåѦçĶŁ
    0.24
    ÑĢÑĥд
    0.24
     evenly
    0.24
    yc
    0.24
    ãĤ·ãĥ¥
    0.24
    icina
    0.24
    éĢĥ
    0.24
    Activations Density 1.201%

    No Known Activations