© 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. 24-TRANSCODER-HP
    7. 150342
    Prev
    Next
    INDEX
    Explanations

    news headlines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tanks
    -0.28
     tank
    -0.26
    åľ¨è¿Ļç§į
    -0.25
    tank
    -0.25
    åİ»åĵªåĦ¿
    -0.25
    ä¹ĸä¹ĸ
    -0.25
    è¿Ļåıª
    -0.25
     chá
    -0.25
     ago
    -0.24
    sand
    -0.24
    POSITIVE LOGITS
     major
    0.28
     former
    0.26
    	initialize
    0.25
     Burl
    0.24
    major
    0.24
    igh
    0.24
    ortic
    0.24
     Äijá»ijc
    0.24
    _advance
    0.24
    积æŀģæĢ§
    0.23
    Activations Density 0.992%

    No Known Activations