© 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. 41425
    Prev
    Next
    INDEX
    Explanations

    connections and relationships

    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
    epam
    -0.27
    èĢĥéªĮ
    -0.25
    IFICATIONS
    -0.24
    衽
    -0.23
     deliveries
    -0.23
    æĮijæĪĺ
    -0.23
     kicker
    -0.23
     drafts
    -0.23
     kicks
    -0.23
     deploying
    -0.23
    POSITIVE LOGITS
     positively
    0.30
    roots
    0.30
     both
    0.30
     deeply
    0.29
     dist
    0.29
     freely
    0.29
     fond
    0.28
     cooper
    0.28
    é¢ľ
    0.28
     easily
    0.28
    Activations Density 0.004%

    No Known Activations