© 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. 20-TRANSCODER-HP
    7. 129572
    Prev
    Next
    INDEX
    Explanations

    Stopwords and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åݻ买
    -0.28
     reserve
    -0.27
    æĺ¯éĿŀ
    -0.27
    landers
    -0.26
    roduce
    -0.26
    åĪ¨
    -0.26
    çĻ¾èĬ±
    -0.26
    å±IJ
    -0.26
    åħ±åĴĮåĽ½
    -0.25
    æĽ´
    -0.24
    POSITIVE LOGITS
    обоÑĢ
    0.33
    otle
    0.28
    arium
    0.26
     guarante
    0.26
     catching
    0.25
    ĺ
    0.25
    utoff
    0.24
     ula
    0.24
     caught
    0.23
     programm
    0.23
    Activations Density 31.822%

    No Known Activations