© 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. 12-TRANSCODER-HP
    7. 22602
    Prev
    Next
    INDEX
    Explanations

    cover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coverage
    -0.29
    coverage
    -0.28
     coverage
    -0.27
    Coverage
    -0.26
     scarc
    -0.25
    fish
    -0.25
    exclusive
    -0.25
     impover
    -0.25
    æ·º
    -0.25
    èµ°åĪ°
    -0.25
    POSITIVE LOGITS
    èī¯å¥½
    0.30
    çĽĴ
    0.30
    æĶ¾å¤§
    0.28
     port
    0.26
    adan
    0.25
     ult
    0.25
     sty
    0.25
     tensor
    0.24
    å¤ļå°ij
    0.24
    æį
    0.24
    Activations Density 0.008%

    No Known Activations