© 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. 163027
    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
    æŀŀ
    -0.28
    pawn
    -0.27
     pickups
    -0.26
    cha
    -0.25
     waivers
    -0.25
    éĹ®ä»ĸ
    -0.25
    让ä»ĸ
    -0.25
    ulan
    -0.24
    actor
    -0.24
    cone
    -0.24
    POSITIVE LOGITS
    [position
    0.28
     Ihr
    0.26
    avery
    0.25
     åŃ
    0.24
    æĺ
    0.24
    éĢĤåIJĪèĩªå·±
    0.24
    merce
    0.23
    æĶ¾å¿ĥ
    0.23
    æ¼ĵ
    0.23
     Amir
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.