© 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. 23-TRANSCODER-HP
    7. 161813
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onents
    -0.27
     Meg
    -0.26
    æľīä»»ä½ķ
    -0.25
     insulation
    -0.25
    Season
    -0.24
    æľīä¿¡å¿ĥ
    -0.24
    寸
    -0.24
    第ä¸Ģå±Ĭ
    -0.23
    idency
    -0.23
    Nonnull
    -0.23
    POSITIVE LOGITS
    称为
    0.29
     setC
    0.29
    åı«åģļ
    0.28
     rh
    0.27
    annot
    0.27
    éĻĦè¿ijçļĦ
    0.27
    _Helper
    0.26
    uvw
    0.25
    åIJį为
    0.23
    åıĪ称
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.