© 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. 23746
    Prev
    Next
    INDEX
    Explanations

    period

    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
    è§Ĩ
    -0.35
    à¹Ħฮ
    -0.25
    unct
    -0.25
    çļĦ妻åŃIJ
    -0.24
    è¦ĸ
    -0.24
    æĢĿæĥ³æĶ¿æ²»
    -0.24
    çļĦ对象
    -0.24
    ymbol
    -0.24
    -aligned
    -0.24
    ãĤ¬ãĤ¤
    -0.24
    POSITIVE LOGITS
    åıijçĥ§
    0.28
    档次
    0.26
    .once
    0.25
     scholarly
    0.25
    ounces
    0.25
    Logger
    0.24
    åŃĺ
    0.24
    ches
    0.24
     Wooden
    0.23
     MagicMock
    0.23
    Activations Density 0.021%

    No Known Activations