© 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. 141982
    Prev
    Next
    INDEX
    Explanations

    Technology/Computing

    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
    åĩºèĩª
    -0.27
    è¿Ļä½į
    -0.26
    è¿ĺ好
    -0.25
    favor
    -0.25
    uries
    -0.25
    åĨĴ
    -0.25
    å¤ļä½į
    -0.24
     mul
    -0.24
     bi
    -0.24
     cita
    -0.24
    POSITIVE LOGITS
    olithic
    0.33
     ÑĤÑĥ
    0.27
    omen
    0.27
    Flo
    0.26
    Hal
    0.25
    rott
    0.25
    tone
    0.25
     flooded
    0.25
    /stats
    0.25
    istrate
    0.24
    Activations Density 21.348%

    No Known Activations