© 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. 20-TRANSCODER-HP
    7. 64583
    Prev
    Next
    INDEX
    Explanations

    Code or system files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºijéĽĨ
    -0.28
    zed
    -0.27
    ylon
    -0.26
    æ£Ģå¯Łå®ĺ
    -0.25
    odb
    -0.25
     HAPP
    -0.24
    ogonal
    -0.24
     glowing
    -0.24
    ccion
    -0.24
    åģļçļĦ
    -0.23
    POSITIVE LOGITS
    erval
    0.30
    âİ
    0.27
    Ai
    0.27
    Na
    0.25
    ely
    0.24
    NA
    0.23
    ighth
    0.23
    éĤ£åıª
    0.23
     noen
    0.23
     Ai
    0.23
    Activations Density 2.749%

    No Known Activations