© 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. 150797
    Prev
    Next
    INDEX
    Explanations

    meaning

    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
    æŃ»è§Ĵ
    -0.25
    ecessary
    -0.24
    меÑģ
    -0.24
    irus
    -0.23
    æµ£
    -0.23
    èīºäºº
    -0.23
    vature
    -0.23
    itness
    -0.22
    åīIJ
    -0.22
    ozy
    -0.22
    POSITIVE LOGITS
     meaning
    0.80
    æĦıä¹ī
    0.78
    åIJ«ä¹ī
    0.76
    çļĦæĦıä¹ī
    0.76
     meanings
    0.70
     Meaning
    0.66
    æĦı義
    0.65
    meaning
    0.61
     significance
    0.58
     interpretation
    0.54
    Activations Density 1.004%

    No Known Activations