© 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. 128893
    Prev
    Next
    INDEX
    Explanations

    C code

    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
    ificant
    -0.30
    åįģéĩĮ
    -0.29
    åİĺ
    -0.25
    asant
    -0.25
     youngsters
    -0.25
    suppress
    -0.24
    .rev
    -0.24
    ãģĦãĤĮãģ°
    -0.24
    [top
    -0.24
     eros
    -0.23
    POSITIVE LOGITS
     AFF
    0.26
    ollah
    0.25
    åij½
    0.25
    æŀ
    0.24
    awah
    0.24
     Aff
    0.24
    éļħ
    0.23
    ç½¾
    0.23
    apist
    0.23
    ittal
    0.23
    Activations Density 0.007%

    No Known Activations