© 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. 27-TRANSCODER-HP
    7. 8196
    Prev
    Next
    INDEX
    Explanations

    end

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÅŁtir
    -0.26
    disposing
    -0.26
    locking
    -0.25
    acement
    -0.25
     factor
    -0.24
    å®ļä»·
    -0.24
    лиÑĩ
    -0.24
    ãģĮãģĭ
    -0.24
    平衡
    -0.24
     connection
    -0.23
    POSITIVE LOGITS
    akan
    0.28
    anders
    0.27
    ä¼¼çļĦ
    0.26
    formats
    0.25
    abis
    0.25
     Nearby
    0.25
    akis
    0.25
    Authorities
    0.24
     Ment
    0.24
    hack
    0.24
    Activations Density 0.001%

    No Known Activations