© 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. 52820
    Prev
    Next
    INDEX
    Explanations

    prepare

    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
    Not in Any Lists

    No Comments

    Negative Logits
     wink
    -0.29
    клÑİÑĩа
    -0.28
    éĩįçĤ¹é¢ĨåŁŁ
    -0.26
    ä¹ĭæĺŁ
    -0.26
    éľĢè¦ģçĶ¨
    -0.25
    æįİ
    -0.25
    æĪIJæŀľè½¬åĮĸ
    -0.25
    ä»ħ代表
    -0.25
    èĥ½çľĭåĩº
    -0.25
    @m
    -0.24
    POSITIVE LOGITS
    better
    0.30
     better
    0.30
     so
    0.29
    енно
    0.28
     Better
    0.28
    æĽ´å¥½
    0.26
     far
    0.25
     vs
    0.25
    åѦçĶŁä»¬
    0.25
    éļ¾
    0.25
    Activations Density 0.016%

    No Known Activations