© 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. 33-TRANSCODER-HP
    7. 54597
    Prev
    Next
    INDEX
    Explanations

    phone calls and services

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -resources
    -0.31
     resource
    -0.28
    è³ĩæºIJ
    -0.28
    èµĦæºIJ
    -0.27
     aff
    -0.26
     process
    -0.25
     resources
    -0.25
    bb
    -0.25
    b
    -0.25
    VERN
    -0.25
    POSITIVE LOGITS
    Dr
    0.32
    _dr
    0.28
    EOF
    0.28
    	doc
    0.26
    doc
    0.26
    æİĴæ¯Ĵ
    0.25
     sabot
    0.25
    umin
    0.25
     cellul
    0.25
     anch
    0.25
    Activations Density 0.007%

    No Known Activations