© 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. 30-TRANSCODER-HP
    7. 96645
    Prev
    Next
    INDEX
    Explanations

    HTML and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amon
    -0.30
    yers
    -0.28
    erce
    -0.28
    æIJħ
    -0.27
    ToPoint
    -0.27
     slugg
    -0.26
    edata
    -0.26
    .toHexString
    -0.25
    ennes
    -0.25
    æĻı
    -0.25
    POSITIVE LOGITS
    麻çĹ¹
    0.28
    平衡
    0.28
     potent
    0.28
    ching
    0.26
     desn
    0.25
    é¢Ĺ
    0.25
    ilities
    0.25
    uced
    0.25
    ç½ij绾
    0.24
     cartel
    0.24
    Activations Density 0.001%

    No Known Activations