© 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. 88763
    Prev
    Next
    INDEX
    Explanations

    even

    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
    ponential
    -0.28
     Bomb
    -0.25
    åĴ«
    -0.25
    åIJĮ缣
    -0.25
    èij¡
    -0.24
    beer
    -0.23
    éħĴ
    -0.23
    hsi
    -0.23
    á»Ĺi
    -0.23
    allis
    -0.23
    POSITIVE LOGITS
     bach
    0.27
    éģĹ
    0.27
     thanks
    0.26
    Sharper
    0.26
    æĢ§å¼º
    0.25
     greetings
    0.25
    ãģĦãģĨ
    0.25
     thank
    0.25
     nghiá»ĩp
    0.25
    CN
    0.24
    Activations Density 23.125%

    No Known Activations