© 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. 89894
    Prev
    Next
    INDEX
    Explanations

    Academic research writing

    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
    æ°ª
    -0.30
    个æĢ§
    -0.29
    ç½
    -0.28
    Thought
    -0.28
    æĢ§æł¼
    -0.27
    çļĦæĢ§æł¼
    -0.27
    以åıĬåħ¶ä»ĸ
    -0.26
    IFE
    -0.26
     quir
    -0.25
     divor
    -0.25
    POSITIVE LOGITS
    èµ°å¾Ĺ
    0.28
    ceeded
    0.28
     record
    0.28
     steps
    0.26
     step
    0.26
    storm
    0.26
     squeezing
    0.26
    á½´
    0.25
    åįĩ
    0.25
     effort
    0.25
    Activations Density 19.223%

    No Known Activations