© 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. 32-TRANSCODER-HP
    7. 43249
    Prev
    Next
    INDEX
    Explanations

    incomplete thoughts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unting
    -0.27
    tod
    -0.26
    ай
    -0.26
    зо
    -0.25
    oders
    -0.25
    isi
    -0.25
    çļĦé¢ľèī²
    -0.24
    _AI
    -0.24
    ABB
    -0.24
    chio
    -0.24
    POSITIVE LOGITS
    pe
    0.27
     packed
    0.26
    å¤ĦçIJĨ
    0.26
    ureen
    0.25
    ê´Ģ리
    0.25
     j
    0.25
     jugg
    0.24
    çīĩ
    0.24
    åĪĨæĪIJ
    0.24
     launches
    0.24
    Activations Density 0.005%

    No Known Activations