© 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. 30-TRANSCODER-HP
    7. 97049
    Prev
    Next
    INDEX
    Explanations

    change

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     physically
    -0.26
    çĶ¨åĬĽ
    -0.25
     ginger
    -0.25
     cref
    -0.25
    çī©çIJĨ
    -0.24
     rely
    -0.24
    iare
    -0.24
    å¹²åĺĽ
    -0.24
    adamente
    -0.24
     sm
    -0.24
    POSITIVE LOGITS
    åıĺåĮĸ
    0.39
    çļĦåıĺåĮĸ
    0.37
    转åıĺ
    0.34
     changing
    0.34
    _change
    0.33
    Change
    0.33
    -change
    0.32
    æį¢äºĨ
    0.32
    changes
    0.32
     Change
    0.32
    Activations Density 0.887%

    No Known Activations