© 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. 33-TRANSCODER-HP
    7. 54601
    Prev
    Next
    INDEX
    Explanations

    Massachusetts cities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     __________________↵↵
    -0.29
    åį¡
    -0.26
    饼
    -0.24
     ';↵↵
    -0.24
    æķĻèĤ²åŁ¹è®Ń
    -0.24
    dde
    -0.24
    BASEPATH
    -0.24
     gef
    -0.23
    èĤ¤
    -0.23
     »↵↵
    -0.23
    POSITIVE LOGITS
    port
    0.33
    MA
    0.32
    me
    0.29
     MA
    0.29
    porto
    0.28
    mary
    0.28
    missive
    0.28
     gene
    0.26
    ÅĪ
    0.25
     char
    0.25
    Activations Density 0.015%

    No Known Activations