© 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. 113002
    Prev
    Next
    INDEX
    Explanations

    Nationalities

    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
     propTypes
    -0.27
    CardBody
    -0.25
    çĵł
    -0.24
    ABI
    -0.24
    è¿Ħ
    -0.23
    NESS
    -0.23
    ä¸ºæľŁ
    -0.23
    è¿Ļä¸Ģå¹´
    -0.23
    åı·
    -0.23
    åĮĸè¿Ľç¨ĭ
    -0.23
    POSITIVE LOGITS
    a
    0.32
    åģĩ
    0.29
    aled
    0.25
    aaaa
    0.25
    åģĩåĨĴ
    0.25
    ner
    0.25
    i
    0.25
    æłĩçļĦ
    0.24
    æħİ
    0.24
    _constraint
    0.24
    Activations Density 0.010%

    No Known Activations