© 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. 161928
    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
    dü
    -0.29
     usu
    -0.27
    _PED
    -0.26
    ç½ijæĬķ
    -0.26
    æĺ¯ä¸Ģ个
    -0.26
    á»Ļng
    -0.26
    æĴĴ
    -0.25
    è¿IJ
    -0.25
    {{{
    -0.25
    æģĴ
    -0.25
    POSITIVE LOGITS
    æĹłå½¢
    0.28
    afone
    0.27
    æĹĭå¾ĭ
    0.25
    otype
    0.25
    å®Įå¤ĩ
    0.25
    igenous
    0.25
    alyze
    0.24
    iones
    0.24
    moz
    0.24
    æIJĶ
    0.24
    Activations Density 0.023%

    No Known Activations

    This feature has no known activations.