© 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. 14-TRANSCODER-HP
    7. 40822
    Prev
    Next
    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĵģ
    -0.27
     bunk
    -0.27
    mind
    -0.27
    ä½İä¸ĭ
    -0.26
    åľ¨æĪijçļĦ
    -0.26
    åľ¨æĪij
    -0.25
    ä¸Ģåı¥
    -0.25
    ore
    -0.25
    ORE
    -0.24
    tv
    -0.24
    POSITIVE LOGITS
     Welch
    0.28
    å¡«åħħ
    0.27
     getCategory
    0.26
    æĬ¥éĢģ
    0.26
    icles
    0.26
    ì¹ł
    0.26
    Roman
    0.26
     Parliamentary
    0.26
    ciÄħg
    0.26
     getState
    0.25
    Activations Density 0.186%

    No Known Activations