© 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. 97229
    Prev
    Next
    INDEX
    Explanations

    learning, discovery

    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
     CAP
    -0.26
     Thomson
    -0.25
     pressured
    -0.25
     Insert
    -0.24
    )<<
    -0.24
     conventional
    -0.24
    odem
    -0.23
    Êĥ
    -0.23
    æıĴåħ¥
    -0.23
    mun
    -0.23
    POSITIVE LOGITS
    äºĨ解
    0.31
    ละ
    0.28
    /sources
    0.27
    çĪ±
    0.27
    -states
    0.25
    anche
    0.25
    äºĨèĩªå·±çļĦ
    0.25
     discovery
    0.25
    (Py
    0.25
     ourselves
    0.25
    Activations Density 0.005%

    No Known Activations