© 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. 109391
    Prev
    Next
    INDEX
    Explanations

    approach

    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
     waivers
    -0.28
     extracted
    -0.24
    ellij
    -0.24
    缸èģļ
    -0.24
    ä¸ĢåĪĨéĴ±
    -0.24
    RU
    -0.24
    pyx
    -0.24
     misconduct
    -0.24
    .Values
    -0.23
    hurst
    -0.23
    POSITIVE LOGITS
    æĢĿè·¯
    0.69
     approach
    0.68
     approaches
    0.63
     approached
    0.57
     Approach
    0.56
    appro
    0.55
     approaching
    0.54
    Appro
    0.50
     Appro
    0.49
    æĢĿèĢĥ
    0.47
    Activations Density 1.147%

    No Known Activations