© 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. 29195
    Prev
    Next
    INDEX
    Explanations

    code/licenses

    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
    è¡Ĺ
    -0.29
    occo
    -0.25
    ün
    -0.25
    exchange
    -0.25
     Peek
    -0.24
     narratives
    -0.24
     purposely
    -0.24
     PICK
    -0.24
    ''↵
    -0.23
    åķī
    -0.23
    POSITIVE LOGITS
     Cair
    0.28
    å¸
    0.28
    cai
    0.27
    æ£Ĵ
    0.26
    çļĦä¸ĵä¸ļ
    0.25
    娥
    0.25
    BUF
    0.25
    ticket
    0.25
     chests
    0.24
     ple
    0.24
    Activations Density 1.164%

    No Known Activations