© 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. 151095
    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_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
    Not in Any Lists

    No Comments

    Negative Logits
     verse
    -0.32
    æķĻæĿIJ
    -0.31
     clauses
    -0.30
     clause
    -0.28
    é¢ĺæĿIJ
    -0.28
     dataset
    -0.27
     rail
    -0.26
     script
    -0.26
    çļĦä½ľåĵģ
    -0.26
     tricky
    -0.26
    POSITIVE LOGITS
    ç§ĺå¯Ĩ
    0.26
    ;br
    0.25
     setuptools
    0.25
    åİĭ
    0.25
    æIJŃè½½
    0.25
     erle
    0.24
     ermög
    0.24
    åħ·ä½ĵæĥħåĨµ
    0.24
    strand
    0.24
    请åģĩ
    0.24
    Activations Density 0.907%

    No Known Activations