© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 90243
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    Negative Logits
    è°ħ
    -0.29
    kills
    -0.28
     má»ģm
    -0.27
    æĮĤåľ¨
    -0.27
    è®®äºĭ
    -0.26
    ço
    -0.25
    ä¸ĢçĤ¹
    -0.25
    antly
    -0.25
     Tent
    -0.25
    igar
    -0.25
    POSITIVE LOGITS
    éĤ£æł·çļĦ
    0.26
    epad
    0.26
    ritch
    0.26
    het
    0.25
     Baxter
    0.24
    rait
    0.24
     Bik
    0.24
    instanc
    0.23
     viá»ĩn
    0.23
    rogram
    0.23
    Activations Density 19.172%

    No Known Activations