© 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. 25-TRANSCODER-HP
    7. 108121
    Prev
    Next
    INDEX
    Explanations

    symbol, code, or math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ²¹èħ»
    -0.25
    ä¸Ģ件äºĭæĥħ
    -0.25
     publicly
    -0.25
    å¿ĥ仪
    -0.25
    åĨħå¹ķ
    -0.24
    amenti
    -0.24
    ä¸įä¼ļæľī
    -0.24
    éĢ¡
    -0.23
    ardin
    -0.23
    ä¹°ä¸ľè¥¿
    -0.23
    POSITIVE LOGITS
     Clem
    0.26
    iants
    0.25
    rib
    0.25
    Fs
    0.25
    depends
    0.24
    GRESS
    0.24
    mag
    0.24
    eward
    0.24
    æĽ´å¥½çļĦ
    0.24
    react
    0.24
    Activations Density 0.986%

    No Known Activations