© 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. 89133
    Prev
    Next
    INDEX
    Explanations

    Improvements, designs, protections

    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
    çĵł
    -0.27
     pakistan
    -0.27
    ARIO
    -0.27
    Tester
    -0.25
    Increases
    -0.25
    å·¥ä½ľèĢħ
    -0.25
    пÑĥÑģ
    -0.25
    arios
    -0.24
    åĴĮæĬĢæľ¯
    -0.24
    ionario
    -0.24
    POSITIVE LOGITS
     ?
    0.28
    Âł
    0.27
     zero
    0.26
    ç»ĦæĪIJ
    0.26
    ãģĻ
    0.26
     dy
    0.25
    åĿIJ
    0.25
     sit
    0.25
    b
    0.25
    鼶
    0.25
    Activations Density 36.862%

    No Known Activations