© 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. 19-TRANSCODER-HP
    7. 7894
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OOM
    -0.30
    海滨
    -0.27
    å·²ä¹ħ
    -0.27
    kop
    -0.26
    Perfect
    -0.26
    æĽ´ä¸º
    -0.25
    *))
    -0.25
    enty
    -0.25
    åĨ³å®ļäºĨ
    -0.25
    borough
    -0.24
    POSITIVE LOGITS
    sbin
    0.28
     subt
    0.27
     assort
    0.26
    两åıª
    0.26
    ADA
    0.26
     warning
    0.24
     trained
    0.24
     async
    0.24
    suming
    0.24
     rest
    0.24
    Activations Density 0.006%

    No Known Activations