© 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. 23-TRANSCODER-HP
    7. 23376
    Prev
    Next
    INDEX
    Explanations

    incoherent/scraped text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     primitive
    -0.26
    sci
    -0.26
     boom
    -0.25
     palindrome
    -0.25
     comm
    -0.24
    _pal
    -0.24
     contr
    -0.24
    ги
    -0.23
     ListNode
    -0.23
    没
    -0.23
    POSITIVE LOGITS
    è¿ĻäºĽéĹ®é¢ĺ
    0.29
    installed
    0.28
    packed
    0.28
    èĢĮåľ¨
    0.28
    èĢĮè¿Ļ
    0.27
    该éĻ¢
    0.27
    ChangeEvent
    0.25
    å¾Ĺä½ı
    0.25
    idget
    0.24
    æľĢåŁºæľ¬çļĦ
    0.24
    Activations Density 0.005%

    No Known Activations