© 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. 52650
    Prev
    Next
    INDEX
    Explanations

    things are affected

    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
    åĨįéĢł
    -0.33
    UCE
    -0.29
    ouv
    -0.26
    æįŁ
    -0.26
    çļĦåİĭåĬĽ
    -0.26
    æģ«
    -0.26
    leans
    -0.25
    宥
    -0.25
    ulado
    -0.25
    Lazy
    -0.25
    POSITIVE LOGITS
     often
    0.30
    常常
    0.27
     fri
    0.26
     a
    0.25
    éĩįéĩį
    0.25
    æī¾åĩĨ
    0.25
     effect
    0.24
    chooser
    0.24
    é¹ī
    0.24
     usually
    0.23
    Activations Density 0.025%

    No Known Activations