© 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. 64295
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     СегоднÑı
    -0.28
    اÙģÙĬ
    -0.26
    æĺİæĹ¥
    -0.25
     tonight
    -0.25
    å¹²æī°
    -0.24
    ktor
    -0.24
    ;element
    -0.24
    Instructions
    -0.24
    alls
    -0.23
    lash
    -0.23
    POSITIVE LOGITS
    Ĩµ
    0.28
    ucken
    0.27
    åĿļå®ļä¸į
    0.26
    rong
    0.26
     Fluent
    0.25
     capture
    0.25
    黾
    0.25
    ftware
    0.25
    éķĩæ±Ł
    0.25
    Else
    0.25
    Activations Density 58.138%

    No Known Activations