© 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. 33-TRANSCODER-HP
    7. 53968
    Prev
    Next
    INDEX
    Explanations

    Finnish related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     big
    -0.30
     cut
    -0.29
     fin
    -0.28
    _big
    -0.27
    Big
    -0.27
     ëĮ
    -0.27
     Big
    -0.27
    ÅĦ
    -0.26
    big
    -0.26
    =c
    -0.26
    POSITIVE LOGITS
    身价
    0.31
    身
    0.29
    rão
    0.24
    anka
    0.24
    追
    0.24
    ä¸ļ
    0.24
    æ´µ
    0.24
    parcel
    0.24
    ä¸ī项
    0.24
     Mun
    0.23
    Activations Density 0.013%

    No Known Activations