© 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. 18-TRANSCODER-HP
    7. 89889
    Prev
    Next
    INDEX
    Explanations

    Technical issues/problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .nlm
    -0.28
     herself
    -0.26
    çĶ©
    -0.26
    侧éĿ¢
    -0.26
    VIOUS
    -0.25
     sola
    -0.24
    PLAIN
    -0.24
    缸åħ³è§Ħå®ļ
    -0.23
    enso
    -0.23
    .extend
    -0.23
    POSITIVE LOGITS
     grit
    0.27
    èµĦ
    0.26
     crunch
    0.25
    éĺ³
    0.25
    à²Ł
    0.24
    æ£ļ
    0.24
    ENCIES
    0.23
    åĵģ
    0.23
    icates
    0.23
    ignon
    0.23
    Activations Density 2.927%

    No Known Activations