© 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. 19-TRANSCODER-HP
    7. 6060
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourse
    -0.28
    chi
    -0.25
    izzato
    -0.25
    quantity
    -0.24
    FormField
    -0.24
    acher
    -0.24
     kilometres
    -0.23
    StackSize
    -0.23
     passé
    -0.23
    æĬĺ
    -0.23
    POSITIVE LOGITS
     OD
    0.28
    ód
    0.27
    åľ¨è¿Ļæĸ¹éĿ¢
    0.26
    两èĢħ
    0.25
    zel
    0.24
    循
    0.24
    æĸ¹éĿ¢
    0.24
    åĬ²
    0.24
    æĺ¯ä¸įåı¯èĥ½
    0.24
     NE
    0.24
    Activations Density 0.010%

    No Known Activations