© 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. 20-TRANSCODER-HP
    7. 62622
    Prev
    Next
    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åłĤ
    -0.28
    积
    -0.28
    pre
    -0.27
    çĪ±
    -0.27
    {name
    -0.27
    ISTA
    -0.26
     Pre
    -0.25
     {}
    -0.25
    .sendStatus
    -0.24
     neither
    -0.24
    POSITIVE LOGITS
    æ¿ĥ
    0.29
    reur
    0.29
    éĴ£
    0.27
    èķĥ
    0.26
    ÑĭÑħ
    0.25
    çݰ身
    0.24
    aud
    0.24
    éĤ®è½®
    0.24
    audi
    0.24
    ä½ľåĵģåĨħ容
    0.24
    Activations Density 10.550%

    No Known Activations