© 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. 130187
    Prev
    Next
    INDEX
    Explanations

    Single-digit numbers

    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
    nard
    -0.29
    gh
    -0.27
    以åıĬåħ¶ä»ĸ
    -0.26
    éªĬ
    -0.25
    MATRIX
    -0.24
    cker
    -0.24
     Conte
    -0.24
    ç»
    -0.24
    agna
    -0.23
    plementary
    -0.23
    POSITIVE LOGITS
    iliar
    0.27
    åħ¸åŀĭçļĦ
    0.25
    ении
    0.25
    æ±īåŃIJ
    0.24
    iten
    0.24
    ä¿¡æģ¯æĬ«éľ²
    0.24
    ä¸ĢèĪ¬çļĦ
    0.24
    èĪŀåı°ä¸Ĭ
    0.24
     Kind
    0.24
    çİ°æľīçļĦ
    0.24
    Activations Density 1.413%

    No Known Activations