© 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. 161631
    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
     probes
    -0.27
    ats
    -0.27
    åĩ¡æľ¬ç½ij
    -0.26
    ä¸Ģ个éĩįè¦ģ
    -0.25
    æİ¢
    -0.25
     cath
    -0.24
    ctions
    -0.24
    æ°´éĩı
    -0.24
    atta
    -0.23
    yp
    -0.23
    POSITIVE LOGITS
    èĢħçļĦ
    0.25
    [end
    0.25
    ivist
    0.25
    æĽ´æĺ¯
    0.23
    _EOL
    0.23
    åŃij
    0.23
     диÑĢекÑĤоÑĢ
    0.23
    Ñıм
    0.23
    [pos
    0.22
    зÑĥ
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.