© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24134
    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
     doubled
    -0.29
    Aspect
    -0.28
    Repeat
    -0.27
    peating
    -0.27
    æ³¥åľŁ
    -0.27
     repeated
    -0.26
    elong
    -0.26
    inky
    -0.26
    idency
    -0.26
    Converted
    -0.26
    POSITIVE LOGITS
     eng
    0.29
     zh
    0.28
     paz
    0.27
    项
    0.27
     na
    0.26
     nov
    0.26
    åĴĮåıijå±ķ
    0.26
    åģıå·®
    0.26
     dzi
    0.26
    ç®Ĺæ³ķ
    0.26
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.