© 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. 20-TRANSCODER-HP
    7. 130052
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ»ŀåIJİ
    -0.31
     WA
    -0.29
    .sys
    -0.26
    ç§ķ
    -0.25
    人们对
    -0.25
     heading
    -0.25
     nuisance
    -0.25
     knock
    -0.24
    åĸij
    -0.24
    æĸ°è¥¿
    -0.24
    POSITIVE LOGITS
     Portions
    0.29
    沫
    0.28
    rone
    0.28
    cznÄħ
    0.27
    å¹³æŶ
    0.26
    ÑĤелÑĮнÑĭе
    0.26
     onCreateView
    0.25
    ëĿ¼ë©´
    0.25
    å½ĵæŶ
    0.24
    ä¸Ģæµģ
    0.24
    Activations Density 4.653%

    No Known Activations