© 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. 97063
    Prev
    Next
    INDEX
    Explanations

    medical topics

    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
    imar
    -0.31
    imeter
    -0.29
    idend
    -0.28
    sett
    -0.28
    éĢł
    -0.27
    ä¹ī
    -0.27
    äºij
    -0.26
    offsetof
    -0.26
    ãģ£
    -0.25
    è¿ĩç¨ĭ
    -0.25
    POSITIVE LOGITS
     planning
    0.31
     issue
    0.29
     control
    0.29
    æݧåĪ¶
    0.27
     pilot
    0.26
    éĺ²èĮĥ
    0.26
     protocols
    0.26
    control
    0.26
     affects
    0.25
    amb
    0.25
    Activations Density 0.897%

    No Known Activations