© 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. 27-TRANSCODER-HP
    7. 57728
    Prev
    Next
    INDEX
    Explanations

    scientific experiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĨåŃIJ
    -0.30
    è¾Ļ
    -0.26
     molecule
    -0.26
    æħ·
    -0.26
     Molecular
    -0.26
     molecular
    -0.26
     lipid
    -0.26
    箬
    -0.25
     molecules
    -0.25
     fat
    -0.25
    POSITIVE LOGITS
     period
    0.30
    ycl
    0.30
    Period
    0.30
     lod
    0.30
     Period
    0.28
     respect
    0.28
     periods
    0.28
     periodic
    0.28
    period
    0.28
    mium
    0.27
    Activations Density 0.001%

    No Known Activations