© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 45
    Prev
    Next
    INDEX
    Explanations

    Software development / Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raised
    -0.31
     interference
    -0.27
     Corpus
    -0.27
    ése
    -0.25
    ób
    -0.25
     mercury
    -0.24
    éĺŁåijĺ
    -0.24
    oves
    -0.24
     removeFrom
    -0.24
     extrad
    -0.23
    POSITIVE LOGITS
    thin
    0.32
    æĹı
    0.29
    æīĺ
    0.26
    -uri
    0.25
    udu
    0.25
     condu
    0.25
    左边
    0.25
    urple
    0.24
    pipe
    0.24
    tparam
    0.24
    Activations Density 0.018%

    No Known Activations