© 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. 96874
    Prev
    Next
    INDEX
    Explanations

    Barbara

    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
    éĩį
    -0.28
     beat
    -0.28
    max
    -0.28
    iane
    -0.27
    çŁ³åĮĸ
    -0.27
    agal
    -0.26
    exual
    -0.25
    beat
    -0.25
    yms
    -0.25
    yll
    -0.25
    POSITIVE LOGITS
    å¼ĢåĬŀ
    0.28
    讹
    0.25
    enthal
    0.24
    ä½łæĥ³
    0.24
    edition
    0.24
    管çIJĨæ°´å¹³
    0.24
    acct
    0.23
    angered
    0.23
    environment
    0.23
     Clip
    0.23
    Activations Density 0.883%

    No Known Activations