© 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. 63556
    Prev
    Next
    INDEX
    Explanations

    stereotype

    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
    Indented
    -0.28
    å¢ŀå¹ħ
    -0.28
    orney
    -0.26
    eni
    -0.26
     nest
    -0.25
    edef
    -0.25
    ·»
    -0.25
    æĮĤåı·
    -0.25
    åł°
    -0.24
     fiber
    -0.24
    POSITIVE LOGITS
     mirrors
    0.26
    åIJĪ
    0.26
     cultures
    0.25
     cult
    0.25
     colours
    0.24
    essim
    0.24
    æī¹è¯Ħ
    0.24
    épo
    0.23
    çļĦåľ°ä½į
    0.23
     favourites
    0.23
    Activations Density 7.414%

    No Known Activations