© 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. 107100
    Prev
    Next
    INDEX
    Explanations

    safety

    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
    AndView
    -0.27
     uniq
    -0.27
    çłļ
    -0.25
    å¤ļä½į
    -0.25
     Templ
    -0.24
     casualties
    -0.24
    éħ¥
    -0.24
    artment
    -0.23
    éļIJå½¢
    -0.23
    avad
    -0.23
    POSITIVE LOGITS
    çīĮ
    0.28
    blind
    0.26
    ware
    0.26
    -oriented
    0.26
    -rest
    0.25
    æĺ¯æ²¡æľī
    0.25
    -conscious
    0.24
    CONN
    0.24
    ä¸Ĭæľī
    0.24
    ozo
    0.24
    Activations Density 1.012%

    No Known Activations