© 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. 142421
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
    izio
    -0.29
    дÑĢ
    -0.28
    å¯ĵ
    -0.26
     prototypes
    -0.26
    è¯ķçĤ¹
    -0.25
    åı¦ä¸Ģè¾¹
    -0.25
    æŃ¤é¡¹
    -0.24
     Rede
    -0.24
    ä¸įè¿ľ
    -0.24
    igation
    -0.23
    POSITIVE LOGITS
    's
    0.27
    æİIJ
    0.26
     ogl
    0.24
     township
    0.24
     handed
    0.24
     ingress
    0.23
    è§Ĩ为
    0.23
    åĽ¾
    0.23
     Vinyl
    0.23
    æµħ
    0.23
    Activations Density 3.509%

    No Known Activations