© 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. 57857
    Prev
    Next
    INDEX
    Explanations

    web pages and technical documents

    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
     efficiency
    -0.54
    æķĪçİĩ
    -0.54
     Efficiency
    -0.46
     efficiencies
    -0.45
     efficient
    -0.41
    å·¥ä½ľæķĪçİĩ
    -0.39
    -eff
    -0.38
    -efficient
    -0.37
    é«ĺæķĪ
    -0.37
     ineff
    -0.36
    POSITIVE LOGITS
     Grat
    0.32
    缺
    0.31
    unsafe
    0.29
    åħ¬åħ±æĸĩåĮĸ
    0.28
    é¡ĺ
    0.27
    Safe
    0.25
    Refresh
    0.25
    _safe
    0.25
    onium
    0.25
    hread
    0.25
    Activations Density 0.001%

    No Known Activations