© 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. 107041
    Prev
    Next
    INDEX
    Explanations

    rats

    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
    berg
    -0.29
    uber
    -0.28
    gence
    -0.27
    éĽĨåIJĪ
    -0.27
    teen
    -0.26
    è¿«
    -0.26
    åĽłæѤ
    -0.26
    nings
    -0.25
    lectric
    -0.25
    BER
    -0.25
    POSITIVE LOGITS
    .mapping
    0.26
    EDIA
    0.26
     nip
    0.26
    åĿ¨
    0.25
    _that
    0.25
     expectancy
    0.25
    ä¸ľè·¯
    0.24
    à¸ģรรม
    0.24
     Americ
    0.24
    appe
    0.24
    Activations Density 0.178%

    No Known Activations