© 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. 22-TRANSCODER-HP
    7. 99234
    Prev
    Next
    INDEX
    Explanations

    venture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     toes
    -0.25
    ukes
    -0.23
    erties
    -0.23
    baugh
    -0.23
    .Dropout
    -0.23
    åľ°ä¸Ń
    -0.23
    ä¸įçĦ¶
    -0.23
    éĿ¢
    -0.23
     longing
    -0.23
    %X
    -0.23
    POSITIVE LOGITS
     joint
    0.30
    èģ¯åIJĪ
    0.29
     Joint
    0.29
    èģĶåIJĪ
    0.28
    ogo
    0.26
    IFO
    0.26
    åıĮæĸ¹
    0.26
     jointly
    0.25
    KeyValuePair
    0.25
    åIJĪä½ľ
    0.25
    Activations Density 0.008%

    No Known Activations