© 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. 33-TRANSCODER-HP
    7. 54835
    Prev
    Next
    INDEX
    Explanations

    reports and articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     $
    -0.28
     most
    -0.27
    £
    -0.26
     ($
    -0.26
     structure
    -0.26
    structure
    -0.25
    ec
    -0.25
    çģ¾éļ¾
    -0.25
    èģĬåŁİ
    -0.25
     ar
    -0.25
    POSITIVE LOGITS
    ä½łä¸į
    0.34
    æĬĬä½ł
    0.30
    çĪ±ä½ł
    0.27
    å¾Īæ¸ħæ¥ļ
    0.27
    ä½łå°±
    0.27
     Bernard
    0.27
    bern
    0.26
    夥
    0.26
    ersed
    0.26
    è®°å½ķ
    0.25
    Activations Density 0.015%

    No Known Activations