© 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. 40798
    Prev
    Next
    INDEX
    Explanations

    bald

    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
    _article
    -0.27
    è¾¾
    -0.27
    clus
    -0.26
    éħŀ
    -0.26
    åĤį
    -0.25
    æĸĩç«ł
    -0.25
     additionally
    -0.25
    icles
    -0.24
    ä¼ļåijĺ
    -0.24
    éģĶ
    -0.24
    POSITIVE LOGITS
    abis
    0.30
    odef
    0.27
    STE
    0.25
     improv
    0.25
    adero
    0.25
    åĬŀ好
    0.24
    å±ı
    0.24
    æ¡£
    0.24
    Ctrls
    0.24
    AVOR
    0.24
    Activations Density 1.427%

    No Known Activations