© 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. 52591
    Prev
    Next
    INDEX
    Explanations

    Legal and criminal activity

    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
     ItemType
    -0.27
    icycle
    -0.27
    cheme
    -0.26
     renew
    -0.26
     itemprop
    -0.26
    ÑĢаÑģÑĤ
    -0.25
    allback
    -0.25
    eyJ
    -0.24
    .addItem
    -0.24
     Glasses
    -0.24
    POSITIVE LOGITS
     mand
    0.29
     will
    0.27
     entering
    0.27
     failure
    0.27
     inf
    0.26
     fusion
    0.26
    èį·
    0.26
     rulings
    0.26
    ODB
    0.25
     nit
    0.25
    Activations Density 0.026%

    No Known Activations