© 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. 107008
    Prev
    Next
    INDEX
    Explanations

    Long

    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
    _countries
    -0.26
    .fail
    -0.26
    çļĦèĦ¸
    -0.26
    dcc
    -0.25
    é¢ĦåħĪ
    -0.25
    fare
    -0.24
    éĺĩ
    -0.24
    缮åīį为æŃ¢
    -0.24
    Ó¨
    -0.24
    åıªæĢķ
    -0.23
    POSITIVE LOGITS
    æł·çļĦ
    0.28
    nze
    0.27
    åħ¬çĶ¨
    0.27
    æĬĦ
    0.26
    uptools
    0.25
    订
    0.25
    æĢ§çļĦ
    0.24
    伪
    0.24
    缼
    0.24
    leton
    0.24
    Activations Density 0.109%

    No Known Activations