© 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. 6036
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æŀ¶
    -0.24
     imper
    -0.24
    éģŀ
    -0.24
    rimp
    -0.23
    ***↵
    -0.23
     drastically
    -0.23
    æ·±åĪ»
    -0.23
    èݪ
    -0.23
    éĢĴ
    -0.23
     Imper
    -0.23
    POSITIVE LOGITS
    èļĵ
    0.29
    满
    0.27
    pins
    0.26
    storm
    0.26
    å¤įåħ´
    0.25
    è¹Ī
    0.25
    缺ä¹ı
    0.25
    æµģ产
    0.25
    igans
    0.25
    ħį
    0.24
    Activations Density 0.906%

    No Known Activations

    This feature has no known activations.