© 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. 23187
    Prev
    Next
    INDEX
    Explanations

    Construction materials

    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
    á»Ń
    -0.28
    æĬ¥ä¸ļ
    -0.26
     domestic
    -0.26
    uart
    -0.25
     localVar
    -0.25
    缴æµģ
    -0.24
    ç§ĥ
    -0.24
    å¾Ħ
    -0.24
    acam
    -0.24
    UART
    -0.24
    POSITIVE LOGITS
     toc
    0.25
    æıIJèµ·
    0.24
     Edu
    0.24
    纽
    0.24
     initialised
    0.24
    InitialState
    0.24
    æī³
    0.23
    izzo
    0.23
    æį¢ä¸ª
    0.23
     budd
    0.23
    Activations Density 0.001%

    No Known Activations