© 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. 129763
    Prev
    Next
    INDEX
    Explanations

    late

    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
     accomplishment
    -0.26
    DialogContent
    -0.26
    åįģåĩłå¹´
    -0.26
    oplevel
    -0.25
     hug
    -0.24
    plied
    -0.24
    ency
    -0.24
    Body
    -0.23
     nin
    -0.23
    ılmÄ±ÅŁ
    -0.23
    POSITIVE LOGITS
    åīģ
    0.28
    åĬłæ²¹
    0.25
    uds
    0.25
    urma
    0.25
    è¯
    0.25
    åľ°è¯´
    0.25
    ä¹Łæĺ¯ä¸Ģç§į
    0.24
    @student
    0.24
    ä¸į便
    0.24
    说å¾Ĺ
    0.24
    Activations Density 7.687%

    No Known Activations