© 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. 96586
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     two
    -0.30
     thousands
    -0.28
     four
    -0.28
    å¹¾åĢĭ
    -0.28
     Thousands
    -0.28
     three
    -0.27
    Thousands
    -0.27
    两çĤ¹
    -0.27
     millions
    -0.27
    å¹¾
    -0.26
    POSITIVE LOGITS
    teen
    0.26
    orte
    0.26
    FTER
    0.25
    fort
    0.24
    erness
    0.24
    evil
    0.24
    elize
    0.24
    鸯
    0.24
    ivic
    0.23
    æģIJæĢĸ
    0.23
    Activations Density 0.083%

    No Known Activations