© 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. 108151
    Prev
    Next
    INDEX
    Explanations

    Code and nonsensical sentences

    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
     Bloody
    -0.26
    stadt
    -0.25
    -company
    -0.25
     sucking
    -0.24
    bp
    -0.24
     $#
    -0.24
    rious
    -0.24
     migrations
    -0.24
     Explos
    -0.24
    itia
    -0.24
    POSITIVE LOGITS
    æīĢåľ¨çļĦ
    0.32
    ä¸įæ¸ħ
    0.29
    enci
    0.27
    èįª
    0.27
    avenport
    0.26
    ä¸ĢæĿ¡
    0.26
    责任
    0.25
    çļĦ责任
    0.25
    ä¹īåĬ¡
    0.24
     recht
    0.24
    Activations Density 0.028%

    No Known Activations