© 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. 8222
    Prev
    Next
    INDEX
    Explanations

    Code and markup text

    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
    illus
    -0.30
                                                    ↵
    -0.25
     ViewData
    -0.25
     pre
    -0.25
    					↵					↵
    -0.23
    habi
    -0.23
     Phot
    -0.23
    ılı
    -0.23
     __________________↵↵
    -0.23
    uche
    -0.22
    POSITIVE LOGITS
    n
    0.31
    e
    0.31
    t
    0.30
    y
    0.29
    çļĦç¨ĭ度
    0.27
     than
    0.27
    çļĦçIJĨæĥ³
    0.26
    çļĦå½¢å¼ı
    0.26
    ,,
    0.26
    r
    0.26
    Activations Density 0.015%

    No Known Activations