© 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. 107293
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    æŀĿ
    -0.26
    æķ¢
    -0.26
    éĢıæĺİ
    -0.25
     hang
    -0.24
    请
    -0.24
    åŁ
    -0.24
    anax
    -0.23
    æĬ¥ä»ĩ
    -0.23
    adata
    -0.23
     pend
    -0.23
    POSITIVE LOGITS
    cter
    0.29
    umer
    0.28
    ãĥĥãĥĪ
    0.25
     preventive
    0.25
     Phelps
    0.24
    Jvm
    0.24
     cer
    0.24
    _lot
    0.24
     exem
    0.23
    qe
    0.23
    Activations Density 0.026%

    No Known Activations