© 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. 89233
    Prev
    Next
    INDEX
    Explanations

    -shift

    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
    æľ¬èº«å°±
    -0.28
    æľ¬èº«
    -0.28
     itself
    -0.27
    ients
    -0.26
    alsa
    -0.25
    稼
    -0.25
     manufact
    -0.24
     Bass
    -0.24
    ĥģ
    -0.24
    enta
    -0.24
    POSITIVE LOGITS
    fetch
    0.30
    imonials
    0.26
    Fetcher
    0.26
    ধ
    0.25
     balloons
    0.25
     liberated
    0.25
    ombine
    0.25
    _relations
    0.25
    鼷æĸ¯
    0.25
    èªįãĤģ
    0.24
    Activations Density 16.278%

    No Known Activations