© 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. 6005
    Prev
    Next
    INDEX
    Explanations

    all

    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
     detail
    -0.27
    otland
    -0.27
    次ä¼ļè®®
    -0.26
    ALA
    -0.26
    intel
    -0.25
     rip
    -0.25
    itional
    -0.24
    æ¸ļ
    -0.23
    bw
    -0.23
    åĵķ
    -0.23
    POSITIVE LOGITS
    åIJĪä¼Ļ人
    0.25
    .getAs
    0.25
    èĤ¥
    0.25
    ulti
    0.24
    ['__
    0.24
    ç©¿æĪ´
    0.24
    æĶ¶
    0.23
    دÙħ
    0.23
    endregion
    0.23
    çĶ³è¯·äºº
    0.23
    Activations Density 1.584%

    No Known Activations