© 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. 27-TRANSCODER-HP
    7. 56404
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Reg
    -0.33
     untrue
    -0.27
     Dev
    -0.26
     Tracking
    -0.26
     reg
    -0.25
     Vit
    -0.25
    大èĴľ
    -0.25
    brahim
    -0.25
     Terr
    -0.24
     Diagram
    -0.24
    POSITIVE LOGITS
    åĽºå®ļçļĦ
    0.29
    æĬ¥
    0.28
     mijn
    0.26
    æĦŁåħ´è¶£çļĦ
    0.26
    alc
    0.25
    	DECLARE
    0.24
    åł±
    0.24
     zab
    0.24
    appa
    0.24
    preh
    0.24
    Activations Density 0.948%

    No Known Activations