© 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. 33-TRANSCODER-HP
    7. 54353
    Prev
    Next
    INDEX
    Explanations

    expresses possibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edImage
    -0.30
    ailand
    -0.28
    imulator
    -0.25
    èģĮä¸ļæĬĢæľ¯
    -0.25
    İĺìĿ´
    -0.24
    èŀº
    -0.24
    æīij
    -0.24
    asurable
    -0.24
     crossorigin
    -0.24
    uffy
    -0.23
    POSITIVE LOGITS
     work
    0.37
    æ¸ħ
    0.34
     Work
    0.30
    åģļè¿ĩ
    0.30
     clean
    0.29
     hal
    0.29
    	work
    0.28
    work
    0.28
     Clean
    0.28
    inker
    0.27
    Activations Density 0.042%

    No Known Activations