© 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. 25072
    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
    æĺ¯ä¸Ģ
    -0.27
    еÑģÑĤи
    -0.26
    æľºæ¢°åĮĸ
    -0.26
    ix
    -0.26
    åį«æĺŁ
    -0.26
    iten
    -0.25
    ä¸Ńåįİ
    -0.25
    æīģ
    -0.25
    ï¼ļ“
    -0.25
     verbally
    -0.24
    POSITIVE LOGITS
    ὶ
    0.26
     moot
    0.24
     hopefully
    0.24
    ãģªãĤĭ
    0.24
     wisely
    0.24
    åijµåijµ
    0.24
     lah
    0.23
    带æĿ¥
    0.23
    Jur
    0.23
     bye
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.