© 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. 30-TRANSCODER-HP
    7. 96898
    Prev
    Next
    INDEX
    Explanations

    3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     seems
    -0.28
     conf
    -0.27
    Che
    -0.27
     seem
    -0.26
     Sea
    -0.26
     CONF
    -0.26
    SEA
    -0.25
     Conf
    -0.25
     seeming
    -0.23
    ä¼¼ä¹İ
    -0.23
    POSITIVE LOGITS
     invent
    0.27
    anity
    0.25
    _la
    0.25
     amplify
    0.25
    ores
    0.25
    ç²ī
    0.24
    èģ
    0.24
    HT
    0.24
    åķ¤
    0.23
    åĮ®
    0.23
    Activations Density 0.001%

    No Known Activations