© 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. 18-TRANSCODER-HP
    7. 89746
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èºį
    -0.29
     frequent
    -0.27
    çī¹æ´¾åijĺ
    -0.26
    omens
    -0.25
    为ä¸Ńå¿ĥ
    -0.25
     viewpoint
    -0.25
    产æĿĥ
    -0.25
     str
    -0.24
    stood
    -0.24
    庶
    -0.24
    POSITIVE LOGITS
    IPS
    0.25
    IQ
    0.25
    try
    0.25
    arb
    0.25
    çļĦå°±æĺ¯
    0.24
    (weights
    0.24
    .setEnabled
    0.24
     try
    0.24
    .addWidget
    0.23
    IXEL
    0.23
    Activations Density 6.945%

    No Known Activations