© 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. 53198
    Prev
    Next
    INDEX
    Explanations

    code/questions/jargon

    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
     caul
    -0.30
    erton
    -0.28
     Show
    -0.28
    æĺ¾
    -0.28
    Show
    -0.27
    VILLE
    -0.26
     show
    -0.26
    尺寸
    -0.25
    æ§
    -0.25
    Illuminate
    -0.25
    POSITIVE LOGITS
    Sus
    0.28
    å·¥ä¸ļ大åѦ
    0.27
    ĮĢ
    0.27
     mig
    0.24
    tor
    0.24
    arend
    0.24
    -addon
    0.24
    æĸ°æĹ¶æľŁ
    0.24
    igg
    0.24
    oom
    0.23
    Activations Density 0.028%

    No Known Activations