© 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. 107243
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    Not in Any Lists

    No Comments

    Negative Logits
    (TEST
    -0.29
     TEST
    -0.27
    [Test
    -0.27
     ìłĢíĿ¬
    -0.26
    çľĭäºĨçľĭ
    -0.26
    æµĭè¯ķ
    -0.26
    TestCase
    -0.26
    è¿Ļå¼ł
    -0.26
    =test
    -0.25
    çŀ»
    -0.25
    POSITIVE LOGITS
    身
    0.30
    奢
    0.27
    åħħåĪĨåıijæĮ¥
    0.26
     descent
    0.26
    zeich
    0.26
     derived
    0.25
    羣å®ŀ
    0.25
     rotations
    0.25
    oref
    0.25
    ä¾¿å®ľ
    0.25
    Activations Density 0.948%

    No Known Activations