© 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. 95135
    Prev
    Next
    INDEX
    Explanations

    1

    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
    社ä¼ļå®ŀè·µ
    -0.28
    大ä¼ļä¸Ĭ
    -0.27
     Surge
    -0.27
     synthetic
    -0.26
    ëŀĢ
    -0.25
    actories
    -0.25
    è¢Ńåĩ»
    -0.25
    caff
    -0.25
    æĪĺçķ¥å¸ĥå±Ģ
    -0.24
    arsers
    -0.24
    POSITIVE LOGITS
    -dom
    0.33
    send
    0.27
     Organizations
    0.27
     send
    0.26
     agr
    0.25
     Osw
    0.25
    cona
    0.24
     O
    0.24
     Dom
    0.24
    ä¸ĭ
    0.24
    Activations Density 0.883%

    No Known Activations