© 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. 25-TRANSCODER-HP
    7. 106936
    Prev
    Next
    INDEX
    Explanations

    Technical Q&A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     masses
    -0.26
    æĪijåİ»
    -0.25
    è¿·èĮ«
    -0.24
    иÑĪÑĮ
    -0.24
    æĭ¥åłµ
    -0.24
    æĺ¯åIJ¦æľī
    -0.23
    åľ°ä¸Ĭ
    -0.23
    ArrayOf
    -0.23
     minions
    -0.23
     palp
    -0.23
    POSITIVE LOGITS
    pection
    0.27
     {}\
    0.26
    essel
    0.25
    ÑĦа
    0.25
    ropy
    0.25
    è°
    0.25
     $$
    0.25
    ullo
    0.25
    ship
    0.24
    rax
    0.24
    Activations Density 1.773%

    No Known Activations