© 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. 30425
    Prev
    Next
    INDEX
    Explanations

    Ben

    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
    主è§Ĥ
    -0.29
    se
    -0.27
    ä¸ĢåĪ»
    -0.25
    ارة
    -0.25
    è§Ĩè§ī
    -0.25
    ä¸ĸ
    -0.24
    PERT
    -0.24
    hta
    -0.24
     intox
    -0.24
    xo
    -0.23
    POSITIVE LOGITS
    åı¼
    0.29
     Fetch
    0.26
     replicated
    0.26
     impres
    0.25
    пÑĢом
    0.25
    érica
    0.25
    ordial
    0.25
    æİ¥è¿ĩ
    0.25
     op
    0.24
     gig
    0.24
    Activations Density 0.726%

    No Known Activations