© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53064
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    èħ¹
    -0.28
    åĮħ袱
    -0.27
    rome
    -0.26
    mess
    -0.26
    Mess
    -0.26
    Sac
    -0.25
     Sac
    -0.25
    æ¸ħæ¾Ī
    -0.25
    amenti
    -0.24
     ment
    -0.24
    POSITIVE LOGITS
    ¾ç¤º
    0.30
    认å®ļ
    0.30
    å¡«
    0.29
    [arr
    0.28
     headline
    0.26
    äºĨä¸Ģ份
    0.26
    é¢ĺ主
    0.25
    çıŃ
    0.25
    第äºĮ次
    0.25
    ander
    0.24
    Activations Density 0.026%

    No Known Activations