© 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. 25391
    Prev
    Next
    INDEX
    Explanations

    Target

    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
     workings
    -0.28
    åĢ¾
    -0.26
    ÅŁ
    -0.25
    åħ±
    -0.25
    ledge
    -0.25
     Sept
    -0.25
     æŃ
    -0.25
    æŃ£å¼ı
    -0.25
    ä¸įåģļ
    -0.24
    声
    -0.24
    POSITIVE LOGITS
    illary
    0.26
     rentals
    0.26
    çļĦ缮åħī
    0.26
    orestation
    0.25
     turnout
    0.25
    =target
    0.25
    _SEL
    0.23
     setDate
    0.23
    quel
    0.23
    oster
    0.23
    Activations Density 0.669%

    No Known Activations