© 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. 30419
    Prev
    Next
    INDEX
    Explanations

    document

    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
    acha
    -0.30
    åѦçĶŁçļĦ
    -0.26
    çĵĴ
    -0.26
    åħįç¨İ
    -0.25
     comb
    -0.25
    Äįe
    -0.25
    aches
    -0.25
     naive
    -0.24
    urge
    -0.24
    ObjectContext
    -0.24
    POSITIVE LOGITS
    æ»ļçIJĥ
    0.29
    念
    0.26
    curity
    0.26
    æĹ¥äº§
    0.26
    åħļå·¥å§Ķ
    0.25
    ))?
    0.25
    unread
    0.25
    >>>(
    0.25
    enary
    0.24
    åºĶ该æĢİä¹Ī
    0.24
    Activations Density 0.561%

    No Known Activations