© 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. 54703
    Prev
    Next
    INDEX
    Explanations

    Music/pop culture references

    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
    war
    -0.31
    kn
    -0.28
    çļĦä¸Ģ大
    -0.27
    Kn
    -0.26
    APPED
    -0.25
     ep
    -0.25
    cap
    -0.25
    appl
    -0.25
    å¼ĢæĪĺ
    -0.25
    ople
    -0.25
    POSITIVE LOGITS
    海绵
    0.27
     Garland
    0.27
    ÙģÙĨ
    0.26
    PACK
    0.26
    =count
    0.25
    anches
    0.25
    个çĻ¾åĪĨ
    0.25
     Ip
    0.25
     Rap
    0.25
     Sponge
    0.25
    Activations Density 0.154%

    No Known Activations