© 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. 88369
    Prev
    Next
    INDEX
    Explanations

    commonly

    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
    lide
    -0.29
    æ»Ĺ
    -0.27
    enever
    -0.26
    éģİä¾Ĩ
    -0.26
    åĥ¹
    -0.26
     Sour
    -0.26
    ä
    -0.25
    ä¸Ģ个éĩįè¦ģ
    -0.25
    ÃŃv
    -0.25
    (sv
    -0.25
    POSITIVE LOGITS
    å®ŀ
    0.30
    éľ²
    0.29
    CG
    0.28
    oling
    0.28
     hugely
    0.26
     behaviour
    0.26
    quipment
    0.25
    èĵ¬
    0.24
     african
    0.24
     consideration
    0.24
    Activations Density 9.812%

    No Known Activations