© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 131107
    Prev
    Next
    INDEX
    Explanations

    period

    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
    Negative Logits
    outlined
    -0.27
     disclosed
    -0.27
    istik
    -0.25
    ometrics
    -0.25
    è§ľ
    -0.24
    åĨħå¿ĥ
    -0.24
    æİĮ声
    -0.23
     outlined
    -0.23
     persönlich
    -0.23
     discipl
    -0.23
    POSITIVE LOGITS
    held
    0.28
    åħĪè¿ĽçļĦ
    0.26
    çļĦç¼ĺæķħ
    0.25
    ÑįÑĢ
    0.25
    -kit
    0.25
    åı¯èĥ½åıijçĶŁ
    0.25
    rop
    0.24
     premium
    0.23
     remains
    0.23
    ä¼ļåıijçĶŁ
    0.23
    Activations Density 3.051%

    No Known Activations