© 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. 54568
    Prev
    Next
    INDEX
    Explanations

    sports news articles

    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
     league
    -0.41
     League
    -0.40
    俱ä¹IJéĥ¨
    -0.37
     club
    -0.36
     clubs
    -0.35
    æīĵæ³ķ
    -0.35
    èģĶèµĽ
    -0.33
    éĺŁ
    -0.33
     squads
    -0.33
     squad
    -0.33
    POSITIVE LOGITS
    hör
    0.27
    æݧèĤ¡éĽĨåĽ¢
    0.25
     unm
    0.24
    trys
    0.24
    å¸Ĥåħ¬å®īå±Ģ
    0.24
    /forms
    0.24
    .getElementsByTagName
    0.24
    éĴĬ
    0.23
    æ´Ĺè¡£æľº
    0.23
     apt
    0.23
    Activations Density 0.456%

    No Known Activations