© 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. 130974
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Assertions
    -0.27
    çĻ¾å®¶
    -0.26
    .depth
    -0.25
    cki
    -0.25
    ,nil
    -0.24
     rowspan
    -0.24
    åįģéĩĮ
    -0.24
    å°½
    -0.24
    iev
    -0.23
    =nil
    -0.23
    POSITIVE LOGITS
    äºĨ
    0.26
     jä
    0.25
    lated
    0.25
    agens
    0.25
    å¼ķèµ·çļĦ
    0.24
     ÐŁÐ¾ÑįÑĤомÑĥ
    0.24
    idders
    0.24
    ding
    0.23
    members
    0.23
    æīįæĺ¯çľŁæŃ£
    0.23
    Activations Density 0.006%

    No Known Activations