© 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. 6102
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    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
    otec
    -0.30
    åĪĽæĸ°èĥ½åĬĽ
    -0.28
     meis
    -0.28
    åħļæł¡
    -0.26
    Accessor
    -0.26
     knobs
    -0.26
    åİļåİļ
    -0.24
    家ãģ®
    -0.24
    ertura
    -0.24
     unr
    -0.24
    POSITIVE LOGITS
    uce
    0.29
    erg
    0.27
    çľł
    0.26
    泡
    0.26
    åħħ足
    0.25
    ä¸ī级
    0.25
    XXXX
    0.25
    ctions
    0.25
     Hours
    0.24
     télé
    0.24
    Activations Density 0.004%

    No Known Activations