© 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. 12-TRANSCODER-HP
    7. 23700
    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_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĴ¤ç¦»
    -0.30
    ictions
    -0.27
     martyr
    -0.27
    æĿĢ
    -0.26
    amment
    -0.25
    .stringify
    -0.25
    å¨ĥ
    -0.25
    âĹ¢
    -0.25
    ä¸Ģè´¯
    -0.25
    undry
    -0.25
    POSITIVE LOGITS
    Fx
    0.28
    RC
    0.28
    -Out
    0.26
     bidi
    0.26
    ingen
    0.26
     writ
    0.25
    建档
    0.25
    ajan
    0.24
    æĿŁ
    0.24
    å¹ħ
    0.24
    Activations Density 0.001%

    No Known Activations