© 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. 140855
    Prev
    Next
    INDEX
    Explanations

    General English sentences

    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
    æIJŃ
    -0.28
    rated
    -0.27
    aclass
    -0.25
    rive
    -0.25
    paces
    -0.25
    arp
    -0.25
    paced
    -0.25
    éĸ£
    -0.24
    å¼ĢåIJ¯äºĨ
    -0.24
    å¥ijæľº
    -0.24
    POSITIVE LOGITS
    èĤ¯å®ļæĺ¯
    0.36
    ä¸į管
    0.33
    ä¸į论
    0.32
    é»ijçĻ½
    0.30
    orden
    0.29
     Whatever
    0.29
    Regardless
    0.28
    Whatever
    0.27
     always
    0.27
    preferences
    0.27
    Activations Density 67.298%

    No Known Activations