© 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. 54277
    Prev
    Next
    INDEX
    Explanations

    Sports related texts

    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
     ga
    -0.31
    妤
    -0.28
    io
    -0.27
    ExecutionContext
    -0.27
    ion
    -0.27
    æ¦Ĩ
    -0.25
    iale
    -0.25
     hive
    -0.24
    core
    -0.24
    ional
    -0.23
    POSITIVE LOGITS
    etes
    0.28
    æĭīåĬ¨
    0.25
    èIJ½
    0.25
    éĺ²æĬ¤
    0.25
    åѦä¼ļ
    0.25
    setPosition
    0.24
    çĪ¬
    0.24
    çıŀ
    0.24
    éħļ
    0.24
    et
    0.24
    Activations Density 0.029%

    No Known Activations