© 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. 63750
    Prev
    Next
    INDEX
    Explanations

    or

    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
    èĥ½ä½¿
    -0.27
     Cup
    -0.26
    aja
    -0.25
    ä¹Łä¸įæķ¢
    -0.24
     nig
    -0.24
    ç©·
    -0.24
    /big
    -0.24
    avia
    -0.24
    ussed
    -0.23
     nickname
    -0.23
    POSITIVE LOGITS
    :hidden
    0.25
    é¢Ĩ导èĢħ
    0.24
    é¢Ĩ导
    0.24
    å¥ijæľº
    0.24
    çļĦä¿¡ä»»
    0.23
     tim
    0.23
    sher
    0.23
    rift
    0.23
    åİ¿åħ¬å®īå±Ģ
    0.22
    AI
    0.22
    Activations Density 1.390%

    No Known Activations