© 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. 25-TRANSCODER-HP
    7. 107119
    Prev
    Next
    INDEX
    Explanations

    could

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     further
    -0.26
    _dispatch
    -0.25
    PointerException
    -0.25
    izen
    -0.25
    Dispatch
    -0.24
    izio
    -0.24
    è¿Ľä¸ĢæŃ¥
    -0.23
    éĹ»
    -0.23
     puts
    -0.23
     topped
    -0.23
    POSITIVE LOGITS
    ellen
    0.28
    æľīä¸Ģ次
    0.26
     [,
    0.25
     haunt
    0.25
    oms
    0.24
    åħ¶
    0.24
    ingen
    0.23
    ieri
    0.23
     it
    0.23
    å¹ķ
    0.23
    Activations Density 0.929%

    No Known Activations