© 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. 41162
    Prev
    Next
    INDEX
    Explanations

    Code/Data

    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
    âĨµ
    -0.28
    è¹Ī
    -0.26
    åħļå§Ķ书记
    -0.26
     ties
    -0.26
    ä¼ļéķ¿
    -0.25
     spin
    -0.24
    lotte
    -0.24
    主ä½ĵ
    -0.24
    cce
    -0.24
     actual
    -0.24
    POSITIVE LOGITS
    ounced
    0.26
    èĮ¸
    0.25
    }:{
    0.24
    è¿ŁåĪ°
    0.24
     Polo
    0.24
    ookie
    0.23
    æĨĭ
    0.23
    Recently
    0.23
    jes
    0.23
    plib
    0.23
    Activations Density 0.541%

    No Known Activations