© 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. 30-TRANSCODER-HP
    7. 96613
    Prev
    Next
    INDEX
    Explanations

    formal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proxy
    -0.29
    (proxy
    -0.28
     Ram
    -0.28
    kowski
    -0.27
     proxies
    -0.27
    éĺ³
    -0.27
    arna
    -0.27
    ine
    -0.26
    -proxy
    -0.26
     IDR
    -0.26
    POSITIVE LOGITS
    Äĺ
    0.28
    ori
    0.27
    -muted
    0.27
     Coverage
    0.27
     EZ
    0.26
     FieldType
    0.26
    führt
    0.26
    coverage
    0.26
     Justice
    0.25
    ãĤ¸ãĥ§
    0.25
    Activations Density 0.991%

    No Known Activations