© 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. 40409
    Prev
    Next
    INDEX
    Explanations

    Years and ages

    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
     pyl
    -0.29
     décou
    -0.28
    è¶ĬæĿ¥è¶Ĭ大
    -0.27
     poop
    -0.26
    variants
    -0.25
     Duis
    -0.25
    æĽ´ä½İ
    -0.25
    æĶ¶æķĽ
    -0.25
    awning
    -0.25
    åĩº
    -0.25
    POSITIVE LOGITS
    æľĢ常è§ģçļĦ
    0.28
     lux
    0.28
    æī§è¡ĮåĬĽ
    0.27
    Wood
    0.26
     Wooden
    0.26
    æī³
    0.26
     wood
    0.25
    æİĸ
    0.25
    -select
    0.25
     Square
    0.25
    Activations Density 0.062%

    No Known Activations