© 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. 24-TRANSCODER-HP
    7. 151355
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     coded
    -0.32
     coding
    -0.27
    æĦ¿
    -0.26
     Brief
    -0.26
     pattern
    -0.25
     brain
    -0.25
     curl
    -0.25
     ant
    -0.25
    Therefore
    -0.25
     meaning
    -0.25
    POSITIVE LOGITS
    ä¸ĭæ²ī
    0.27
     slag
    0.26
    å°¸ä½ĵ
    0.25
    缸çķ¶
    0.25
    ApiClient
    0.25
    ending
    0.24
    lobber
    0.24
    Ñĥй
    0.24
    ording
    0.23
     scre
    0.23
    Activations Density 0.138%

    No Known Activations