© 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. 22-TRANSCODER-HP
    7. 86912
    Prev
    Next
    INDEX
    Explanations

    Scientific/medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĮħæĭ¬
    -0.61
     including
    -0.58
    including
    -0.50
     Including
    -0.48
    INCLUDING
    -0.44
    åį³
    -0.43
    Including
    -0.43
     INCLUDING
    -0.38
    —including
    -0.36
    åħ¶ä¸ŃåĮħæĭ¬
    -0.34
    POSITIVE LOGITS
    _Abstract
    0.30
    onio
    0.27
     &_
    0.27
    ust
    0.26
    æĪij说
    0.26
    pus
    0.25
     $?
    0.24
    å½ķåĪ¶
    0.24
    åħ«å¤§
    0.24
    çľļ
    0.24
    Activations Density 0.005%

    No Known Activations