© 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. 43430
    Prev
    Next
    INDEX
    Explanations

    Code or research snippets

    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
     strong
    -0.60
     Strong
    -0.53
     strength
    -0.51
    强
    -0.49
    å¼·
    -0.47
    Strong
    -0.47
    strong
    -0.46
     core
    -0.46
     strongest
    -0.45
    æł¸å¿ĥ
    -0.45
    POSITIVE LOGITS
    èµĦ产
    0.30
    JOB
    0.30
     Portfolio
    0.28
    Portfolio
    0.27
    Job
    0.27
    -os
    0.26
     Job
    0.25
    æĥħ人
    0.25
    çĨµ
    0.25
     portfolio
    0.24
    Activations Density 0.003%

    No Known Activations