© 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. 112866
    Prev
    Next
    INDEX
    Explanations

    provider

    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
    Not in Any Lists

    No Comments

    Negative Logits
    opic
    -0.29
    èĪĪ
    -0.25
    bred
    -0.24
    ythe
    -0.24
    )arg
    -0.24
     prêt
    -0.24
     bevor
    -0.23
     //'
    -0.23
     proof
    -0.23
    ãģĵãģĵãģ¾ãģ§
    -0.23
    POSITIVE LOGITS
    ugo
    0.27
    iants
    0.25
    iant
    0.25
    /ne
    0.24
    omore
    0.24
    elocity
    0.24
     encount
    0.24
    CHA
    0.24
    è¿Ļ个èģĮä¸ļ
    0.24
    帮åĬ©
    0.23
    Activations Density 0.081%

    No Known Activations