© 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. 96407
    Prev
    Next
    INDEX
    Explanations

    Code/mathematics text

    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
    èįĥ
    -0.35
    äºļ
    -0.30
    ças
    -0.27
     financial
    -0.27
    çł¥
    -0.26
     flame
    -0.26
    迳
    -0.26
    ki
    -0.26
    èľĤ
    -0.26
    ail
    -0.26
    POSITIVE LOGITS
    boBox
    0.25
    .onError
    0.25
    HITE
    0.25
    StateException
    0.25
    RowAt
    0.24
    äºĶæĺŁ
    0.24
    å½¼
    0.24
    eron
    0.24
    )init
    0.24
    VERSE
    0.23
    Activations Density 0.902%

    No Known Activations