© 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. 108107
    Prev
    Next
    INDEX
    Explanations

    inventions

    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
     anyway
    -0.28
    yn
    -0.26
     prov
    -0.26
    èĩªçĶ±
    -0.25
    åĢĴ
    -0.25
     overlap
    -0.24
     ..
    -0.24
     economy
    -0.24
    edy
    -0.24
    æĪijä¸Ģ缴
    -0.24
    POSITIVE LOGITS
    æĶ¶æķĽ
    0.27
    cludes
    0.27
     getInt
    0.26
     getClient
    0.25
    rus
    0.25
    æĪĴ
    0.25
    æŀ¹
    0.24
    è¶Ĭ大
    0.24
    ãĥıãĤ¦ãĤ¹
    0.23
    çļĦèĦļæŃ¥
    0.23
    Activations Density 5.782%

    No Known Activations