© 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. 6420
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     conv
    -0.29
    nin
    -0.26
     ref
    -0.25
     cola
    -0.24
    conv
    -0.24
    ainen
    -0.23
     reco
    -0.23
    èĪĪ
    -0.23
    angen
    -0.23
    jin
    -0.23
    POSITIVE LOGITS
     #%
    0.26
    ')."
    0.25
    æ£ļ
    0.25
    çħŀ
    0.24
    ç§ijæĬĢè¿ĽæŃ¥
    0.23
    åĪ¨
    0.23
    ï¼ģ');↵
    0.22
    //{↵
    0.22
    avia
    0.22
    %s
    0.22
    Activations Density 0.012%

    No Known Activations