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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 80
    Prev
    Next
    INDEX
    Explanations

    Lynch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dev
    -0.26
    mez
    -0.26
     Meter
    -0.25
    annies
    -0.24
     gj
    -0.24
    åij¨å¹´
    -0.24
     fle
    -0.24
    gel
    -0.23
     iff
    -0.23
     tuned
    -0.23
    POSITIVE LOGITS
    ä»ĸçŁ¥éģĵ
    0.27
    çĻĸ
    0.27
    ä»ĸ认为
    0.27
    é¢ł
    0.26
     proceeds
    0.26
    _QUAL
    0.25
    çŁ
    0.25
     voyeur
    0.25
    çļĦè´¨éĩı
    0.25
    æĺ¯å¯¹
    0.25
    Activations Density 0.027%

    No Known Activations