© 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. 108854
    Prev
    Next
    INDEX
    Explanations

    Malware and computer code

    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
    ensem
    -0.28
    <data
    -0.28
    undra
    -0.28
     tighter
    -0.27
     upfront
    -0.27
    cca
    -0.27
     copyrights
    -0.26
     performance
    -0.25
     depos
    -0.24
     AAA
    -0.24
    POSITIVE LOGITS
     infect
    0.29
    Bars
    0.28
    æİĴè¡Į
    0.28
    æ¯į
    0.27
    orable
    0.27
    .vn
    0.27
    lyph
    0.26
    обÑĭ
    0.26
    ä¼łæŁĵ
    0.26
    并ä¸įèĥ½
    0.26
    Activations Density 0.919%

    No Known Activations