© 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. 108363
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    gregated
    -0.27
    æķĪ
    -0.25
    pgsql
    -0.25
     end
    -0.24
     NGX
    -0.24
     onset
    -0.24
    кал
    -0.24
     passports
    -0.23
    endez
    -0.23
    пÑĥÑģ
    -0.23
    POSITIVE LOGITS
    orc
    0.25
    -thumb
    0.25
    å±ŀäºİ
    0.24
    åĴª
    0.24
    æ¯Ķä¾ĭ
    0.24
    ze
    0.23
    kke
    0.23
    æĹ¥åĩĮæĻ¨
    0.23
    ëĦ¤ìļĶ
    0.23
    Naming
    0.23
    Activations Density 43.746%

    No Known Activations

    This feature has no known activations.