© 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. 56983
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    ä¹ł
    -0.27
    ä¼ĺåħĪ
    -0.26
     strike
    -0.26
     rak
    -0.25
     train
    -0.25
    LAN
    -0.24
    .gstatic
    -0.24
     stre
    -0.24
     sit
    -0.24
    train
    -0.23
    POSITIVE LOGITS
    quam
    0.34
    å½ĵåīįä½įç½®
    0.31
     peter
    0.25
     Tomas
    0.25
    èµŀ
    0.25
    è¿ģ
    0.25
    evin
    0.25
    ä¸įæĪIJ
    0.24
    Úĺ
    0.24
    ön
    0.24
    Activations Density 0.000%

    No Known Activations