© 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. 64460
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    æĺ¯åIJ¦ä¼ļ
    -0.27
    ä¼ļä¸įä¼ļ
    -0.26
    åħīéĺ´
    -0.25
    icia
    -0.24
     Belg
    -0.24
    oes
    -0.24
    éĹªçĥģ
    -0.24
    èij¶
    -0.24
    <Vertex
    -0.24
    èĺħ
    -0.24
    POSITIVE LOGITS
    åħ·
    0.32
    O
    0.29
    åĪĹ
    0.28
    mounted
    0.28
    oundation
    0.27
    éĻ¤éĿŀ
    0.25
     Coach
    0.25
    æĦ¿æĻ¯
    0.24
    éĿŀ
    0.24
    æľºæ¢°è®¾å¤ĩ
    0.24
    Activations Density 8.648%

    No Known Activations