© 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. 87123
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
    好人
    -0.28
    åį³æŶ
    -0.26
    éļĶ离
    -0.25
     incons
    -0.24
    åħ¶å®ĥéĹ®é¢ĺ
    -0.24
     Tiny
    -0.24
    åĴ±
    -0.24
    à¹Ģลย
    -0.24
    æĦı大
    -0.24
     Benton
    -0.23
    POSITIVE LOGITS
    ural
    0.28
     khảo
    0.27
    edReader
    0.26
    icip
    0.26
    ValueCollection
    0.26
    lem
    0.24
    sim
    0.24
     :↵↵↵↵
    0.24
    aud
    0.23
    clipse
    0.23
    Activations Density 0.063%

    No Known Activations