© 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. 9243
    Prev
    Next
    INDEX
    Explanations

    Geographical areas and land

    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
     early
    -0.29
    loat
    -0.25
     Early
    -0.24
     AREA
    -0.24
    enet
    -0.24
    æĹ©æľŁ
    -0.23
     appar
    -0.23
    äºĶæĺŁ
    -0.23
    alen
    -0.23
    ilters
    -0.22
    POSITIVE LOGITS
    åŁİéķĩ
    0.25
    UDA
    0.25
     Pa
    0.24
     spiked
    0.24
    _pa
    0.24
    éĥ½å¸Ĥ
    0.24
    被çĽĹ
    0.24
    ülü
    0.24
     Tyson
    0.24
    VRT
    0.23
    Activations Density 0.003%

    No Known Activations