© 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. 99189
    Prev
    Next
    INDEX
    Explanations

    rather

    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
    >List
    -0.27
    vg
    -0.25
     heels
    -0.25
    ;element
    -0.25
    addock
    -0.25
    –
    -0.24
    æŀģåħ¶
    -0.24
    edReader
    -0.24
    agedList
    -0.23
    ante
    -0.23
    POSITIVE LOGITS
    instead
    0.28
     instead
    0.27
    ittel
    0.27
    /url
    0.26
    (cin
    0.25
     traditionally
    0.25
    cid
    0.25
    íĮĶ
    0.25
    traditional
    0.25
     traditional
    0.25
    Activations Density 0.018%

    No Known Activations