© 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. 129158
    Prev
    Next
    INDEX
    Explanations

    a/an

    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
    ocity
    -0.26
    	resource
    -0.26
    plier
    -0.26
    Constructed
    -0.25
    èµĦæºIJ
    -0.25
    DCF
    -0.25
     Taco
    -0.24
    åº
    -0.24
    cellent
    -0.24
    çľ¼çķĮ
    -0.24
    POSITIVE LOGITS
    isz
    0.27
    æľīæľº
    0.26
     Sy
    0.26
     Ont
    0.26
     states
    0.26
    ont
    0.25
    ój
    0.25
    ä¸į满
    0.25
    转åĮĸ为
    0.25
    -only
    0.25
    Activations Density 0.011%

    No Known Activations