© 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. 9-TRANSCODER-HP
    7. 30490
    Prev
    Next
    INDEX
    Explanations

    Law and Commerce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    har
    -0.27
    éŀł
    -0.26
    å½±åĵį
    -0.25
    æĺİçıł
    -0.25
    åĽ¢éķ¿
    -0.24
    ateur
    -0.24
    éĦĻ
    -0.24
    lav
    -0.24
    akest
    -0.24
    rome
    -0.24
    POSITIVE LOGITS
     parks
    0.31
    oria
    0.30
    ä¸ĭæ²ī
    0.28
     CDDL
    0.26
     Witt
    0.26
    çĮ©
    0.26
    æĪª
    0.25
    æī©
    0.25
    ä¸ĭè½½
    0.24
    TOT
    0.24
    Activations Density 0.407%

    No Known Activations