© 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. 19045
    Prev
    Next
    INDEX
    Explanations

    Sil

    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
    缪
    -0.29
    orts
    -0.27
    aland
    -0.27
     BOTTOM
    -0.27
    @register
    -0.25
    ä¼ģ
    -0.24
     bottom
    -0.24
     bottoms
    -0.24
     Rouge
    -0.24
    åºķ
    -0.24
    POSITIVE LOGITS
    褥
    0.28
    agara
    0.28
    aff
    0.28
    Rated
    0.25
    peon
    0.25
     Shall
    0.24
    eri
    0.24
    ãĥ¬ãĥĵãĥ¥ãĥ¼
    0.24
    å¤ĸåĮħ
    0.24
     Aff
    0.24
    Activations Density 0.008%

    No Known Activations