© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25510
    Prev
    Next
    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
     supervision
    -0.36
     control
    -0.33
     Control
    -0.32
    管è¾ĸ
    -0.32
     Superv
    -0.31
    	control
    -0.30
     oversight
    -0.30
    æݧåĪ¶
    -0.28
    control
    -0.28
    .control
    -0.28
    POSITIVE LOGITS
    éĶIJ
    0.29
    enis
    0.26
    è¢ĭ
    0.26
    裱
    0.26
    osa
    0.25
     %(
    0.25
    èĢĥèĻij
    0.24
     /
    0.24
    iator
    0.24
    æĻ°
    0.24
    Activations Density 0.045%

    No Known Activations