© 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. 130350
    Prev
    Next
    INDEX
    Explanations

    Description

    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
    enef
    -0.29
    ourg
    -0.28
    ANGO
    -0.26
    quo
    -0.25
    uld
    -0.24
    licity
    -0.24
    ething
    -0.24
    ocking
    -0.24
     unveiling
    -0.24
    æİĴ污
    -0.23
    POSITIVE LOGITS
    主è¦ģ
    0.27
    为ä¸Ńå¿ĥ
    0.26
    ped
    0.25
     вÑģÑİ
    0.25
    irl
    0.25
     extent
    0.25
    顶
    0.25
    rael
    0.25
    å½ĵä¸Ń
    0.24
     area
    0.24
    Activations Density 1.769%

    No Known Activations