© 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. 24-TRANSCODER-HP
    7. 151021
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptive
    -0.29
    æĬī
    -0.25
    ders
    -0.25
    brig
    -0.24
    abar
    -0.24
    venes
    -0.24
     Whatever
    -0.24
    oggled
    -0.24
    APO
    -0.24
    sonian
    -0.23
    POSITIVE LOGITS
    åĩłæ¬¡
    0.82
    æľīä¸Ģ次
    0.72
    å¤ļ次
    0.66
    ä¸Ģ次
    0.62
    ä¸ī次
    0.57
    两次
    0.54
     several
    0.53
    æĹłæķ°æ¬¡
    0.52
    ä¸įå°ij
    0.49
    åĩłä¸ª
    0.47
    Activations Density 1.053%

    No Known Activations