© 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. 9-TRANSCODER-HP
    7. 29861
    Prev
    Next
    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rub
    -0.26
    åģļå®Į
    -0.25
    Best
    -0.25
    UBL
    -0.25
    æݬ
    -0.25
     pus
    -0.25
    èĭ·
    -0.25
    åĬŀ好
    -0.24
    ublic
    -0.24
    ub
    -0.24
    POSITIVE LOGITS
     Tie
    0.28
    ogy
    0.28
     tie
    0.26
    à¸Ńà¸Ńà¸Ļà¹Ħล
    0.26
    ä»ĸ认为
    0.26
    blocking
    0.25
    .ny
    0.24
    iqu
    0.24
    å¹²éĥ¨
    0.24
    æĤ¨åIJĮæĦı
    0.24
    Activations Density 2.050%

    No Known Activations