© 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. 20-TRANSCODER-HP
    7. 130163
    Prev
    Next
    INDEX
    Explanations

    Internet text

    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
    aura
    -0.26
    åŀ£
    -0.25
     trá»Ŀi
    -0.25
     amat
    -0.25
     Baker
    -0.24
    iative
    -0.24
     intimidated
    -0.24
     dart
    -0.23
    æ´»è·ĥ
    -0.23
    æ¯ıä¸Ģ个
    -0.23
    POSITIVE LOGITS
    ,</
    0.27
    æłijæŀĹ
    0.26
    æĸ°éĹ»åıijå¸ĥ
    0.25
    -</
    0.25
     trick
    0.24
     '</
    0.24
    æĿµ
    0.24
     clic
    0.23
    æķĿ
    0.23
    Ùģص
    0.23
    Activations Density 0.754%

    No Known Activations