© 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. 162906
    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
    phin
    -0.29
    æĹłè¾ľ
    -0.27
     Bene
    -0.26
     kali
    -0.26
    æ¹¾åĮº
    -0.25
    èĢĮåĩº
    -0.25
    SAN
    -0.24
    olor
    -0.24
    ortho
    -0.24
    没äºĭ
    -0.24
    POSITIVE LOGITS
     preliminary
    0.32
    æĪ´
    0.28
     borrowing
    0.27
     prelim
    0.26
    .Unmarshal
    0.26
    ymes
    0.25
     weekly
    0.25
     Prel
    0.25
     helm
    0.25
    åĪĿæŃ¥
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.