© 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. 150961
    Prev
    Next
    INDEX
    Explanations

    light and radiation

    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
     Taste
    -0.35
    éĴ©
    -0.29
    barang
    -0.28
    çķ«
    -0.28
    æ»´
    -0.27
    齿
    -0.27
    wash
    -0.27
    éĨ®
    -0.27
    egra
    -0.26
    videos
    -0.26
    POSITIVE LOGITS
     rays
    0.49
     radiation
    0.47
    çħ§å°Ħ
    0.45
     sunlight
    0.44
     ray
    0.43
     reflection
    0.42
     reflected
    0.41
     light
    0.40
    reflection
    0.40
     wavelengths
    0.39
    Activations Density 1.335%

    No Known Activations