© 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. 109364
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
     indiv
    -0.28
    ebb
    -0.27
    çīĩ
    -0.26
    oney
    -0.25
    èĥ¨
    -0.25
    æ·»
    -0.24
    PWD
    -0.24
    -sensitive
    -0.24
     deeply
    -0.24
    æĴĤ
    -0.23
    POSITIVE LOGITS
    çĹķ迹
    0.25
    çĪ¬
    0.25
    ,,,
    0.25
    ä»Ģä¹Īäºĭ
    0.24
    两åıª
    0.23
    .Contracts
    0.23
    ilot
    0.23
    尾巴
    0.23
    çªģåĩ»
    0.23
    \"]
    0.23
    Activations Density 0.331%

    No Known Activations