© 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. 5151
    Prev
    Next
    INDEX
    Explanations

    structured text

    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
    ä¸Ģç§į
    -0.25
    çīĪæĿĥæīĢæľī
    -0.25
    è¿Ľä¸ĢæŃ¥
    -0.25
    ç§į
    -0.25
    abad
    -0.24
     ded
    -0.24
     unique
    -0.24
    æĻļ
    -0.24
     further
    -0.23
    owski
    -0.23
    POSITIVE LOGITS
    hf
    0.27
    å¸Ļ
    0.25
    _STS
    0.25
    EMS
    0.25
    IGN
    0.25
    wear
    0.24
    egis
    0.24
    icht
    0.24
    lobe
    0.24
     ry
    0.24
    Activations Density 0.040%

    No Known Activations