© 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. 31-TRANSCODER-HP
    7. 18457
    Prev
    Next
    INDEX
    Explanations

    Societal issues and health

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŁĦ
    -0.28
     Larson
    -0.28
    slice
    -0.27
    ÑĢей
    -0.26
    åĬ¨éĿĻ
    -0.26
    æ¨¡æł·
    -0.25
    (ent
    -0.25
    æĨ¾
    -0.24
    åłij
    -0.24
    ubbo
    -0.24
    POSITIVE LOGITS
     air
    0.37
    空æ°Ķ
    0.32
     population
    0.30
    ines
    0.29
    omic
    0.28
    imes
    0.27
    oine
    0.27
    空
    0.27
     populations
    0.26
    OMIC
    0.26
    Activations Density 27.889%

    No Known Activations